diff options
Diffstat (limited to 'net/core')
40 files changed, 2616 insertions, 1227 deletions
diff --git a/net/core/Makefile b/net/core/Makefile index d9326600e289..b2a76ce33932 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -9,7 +9,7 @@ obj-y := sock.o request_sock.o skbuff.o datagram.o stream.o scm.o \ obj-$(CONFIG_SYSCTL) += sysctl_net_core.o -obj-y += dev.o dev_addr_lists.o dst.o netevent.o \ +obj-y += dev.o dev_api.o dev_addr_lists.o dst.o netevent.o \ neighbour.o rtnetlink.o utils.o link_watch.o filter.o \ sock_diag.o dev_ioctl.o tso.o sock_reuseport.o \ fib_notifier.o xdp.o flow_offload.o gro.o \ @@ -45,5 +45,5 @@ obj-$(CONFIG_BPF_SYSCALL) += bpf_sk_storage.o obj-$(CONFIG_OF) += of_net.o obj-$(CONFIG_NET_TEST) += net_test.o obj-$(CONFIG_NET_DEVMEM) += devmem.o -obj-$(CONFIG_DEBUG_NET_SMALL_RTNL) += rtnl_net_debug.o +obj-$(CONFIG_DEBUG_NET) += lock_debug.o obj-$(CONFIG_FAIL_SKB_REALLOC) += skb_fault_injection.o diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c index 7d41cde1bcca..2e538399757f 100644 --- a/net/core/bpf_sk_storage.c +++ b/net/core/bpf_sk_storage.c @@ -355,11 +355,6 @@ const struct bpf_func_proto bpf_sk_storage_delete_proto = { static bool bpf_sk_storage_tracing_allowed(const struct bpf_prog *prog) { - const struct btf *btf_vmlinux; - const struct btf_type *t; - const char *tname; - u32 btf_id; - if (prog->aux->dst_prog) return false; @@ -374,13 +369,7 @@ static bool bpf_sk_storage_tracing_allowed(const struct bpf_prog *prog) return true; case BPF_TRACE_FENTRY: case BPF_TRACE_FEXIT: - btf_vmlinux = bpf_get_btf_vmlinux(); - if (IS_ERR_OR_NULL(btf_vmlinux)) - return false; - btf_id = prog->aux->attach_btf_id; - t = btf_type_by_id(btf_vmlinux, btf_id); - tname = btf_name_by_offset(btf_vmlinux, t->name_off); - return !!strncmp(tname, "bpf_sk_storage", + return !!strncmp(prog->aux->attach_func_name, "bpf_sk_storage", strlen("bpf_sk_storage")); default: return false; diff --git a/net/core/dev.c b/net/core/dev.c index c0021cbd28fc..0608605cfc24 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -156,9 +156,11 @@ #include <linux/pm_runtime.h> #include <linux/prandom.h> #include <linux/once_lite.h> +#include <net/netdev_lock.h> #include <net/netdev_rx_queue.h> #include <net/page_pool/types.h> #include <net/page_pool/helpers.h> +#include <net/page_pool/memory_provider.h> #include <net/rps.h> #include <linux/phy_link_topology.h> @@ -570,10 +572,18 @@ static inline void netdev_set_addr_lockdep_class(struct net_device *dev) static inline struct list_head *ptype_head(const struct packet_type *pt) { - if (pt->type == htons(ETH_P_ALL)) - return pt->dev ? &pt->dev->ptype_all : &net_hotdata.ptype_all; - else - return pt->dev ? &pt->dev->ptype_specific : + if (pt->type == htons(ETH_P_ALL)) { + if (!pt->af_packet_net && !pt->dev) + return NULL; + + return pt->dev ? &pt->dev->ptype_all : + &pt->af_packet_net->ptype_all; + } + + if (pt->dev) + return &pt->dev->ptype_specific; + + return pt->af_packet_net ? &pt->af_packet_net->ptype_specific : &ptype_base[ntohs(pt->type) & PTYPE_HASH_MASK]; } @@ -594,6 +604,9 @@ void dev_add_pack(struct packet_type *pt) { struct list_head *head = ptype_head(pt); + if (WARN_ON_ONCE(!head)) + return; + spin_lock(&ptype_lock); list_add_rcu(&pt->list, head); spin_unlock(&ptype_lock); @@ -618,6 +631,9 @@ void __dev_remove_pack(struct packet_type *pt) struct list_head *head = ptype_head(pt); struct packet_type *pt1; + if (!head) + return; + spin_lock(&ptype_lock); list_for_each_entry(pt1, head, list) { @@ -1007,7 +1023,7 @@ struct net_device *dev_get_by_napi_id(unsigned int napi_id) WARN_ON_ONCE(!rcu_read_lock_held()); - if (napi_id < MIN_NAPI_ID) + if (!napi_id_valid(napi_id)) return NULL; napi = napi_by_id(napi_id); @@ -1121,6 +1137,12 @@ out: return ret; } +static bool dev_addr_cmp(struct net_device *dev, unsigned short type, + const char *ha) +{ + return dev->type == type && !memcmp(dev->dev_addr, ha, dev->addr_len); +} + /** * dev_getbyhwaddr_rcu - find a device by its hardware address * @net: the applicable net namespace @@ -1129,7 +1151,7 @@ out: * * Search for an interface by MAC address. Returns NULL if the device * is not found or a pointer to the device. - * The caller must hold RCU or RTNL. + * The caller must hold RCU. * The returned device has not had its ref count increased * and the caller must therefore be careful about locking * @@ -1141,14 +1163,39 @@ struct net_device *dev_getbyhwaddr_rcu(struct net *net, unsigned short type, struct net_device *dev; for_each_netdev_rcu(net, dev) - if (dev->type == type && - !memcmp(dev->dev_addr, ha, dev->addr_len)) + if (dev_addr_cmp(dev, type, ha)) return dev; return NULL; } EXPORT_SYMBOL(dev_getbyhwaddr_rcu); +/** + * dev_getbyhwaddr() - find a device by its hardware address + * @net: the applicable net namespace + * @type: media type of device + * @ha: hardware address + * + * Similar to dev_getbyhwaddr_rcu(), but the owner needs to hold + * rtnl_lock. + * + * Context: rtnl_lock() must be held. + * Return: pointer to the net_device, or NULL if not found + */ +struct net_device *dev_getbyhwaddr(struct net *net, unsigned short type, + const char *ha) +{ + struct net_device *dev; + + ASSERT_RTNL(); + for_each_netdev(net, dev) + if (dev_addr_cmp(dev, type, ha)) + return dev; + + return NULL; +} +EXPORT_SYMBOL(dev_getbyhwaddr); + struct net_device *dev_getfirstbyhwtype(struct net *net, unsigned short type) { struct net_device *dev, *ret = NULL; @@ -1339,15 +1386,7 @@ static int dev_get_valid_name(struct net *net, struct net_device *dev, return ret < 0 ? ret : 0; } -/** - * dev_change_name - change name of a device - * @dev: device - * @newname: name (or format string) must be at least IFNAMSIZ - * - * Change name of a device, can pass format strings "eth%d". - * for wildcarding. - */ -int dev_change_name(struct net_device *dev, const char *newname) +int netif_change_name(struct net_device *dev, const char *newname) { struct net *net = dev_net(dev); unsigned char old_assign_type; @@ -1417,15 +1456,7 @@ rollback: return err; } -/** - * dev_set_alias - change ifalias of a device - * @dev: device - * @alias: name up to IFALIASZ - * @len: limit of bytes to copy from info - * - * Set ifalias for a device, - */ -int dev_set_alias(struct net_device *dev, const char *alias, size_t len) +int netif_set_alias(struct net_device *dev, const char *alias, size_t len) { struct dev_ifalias *new_alias = NULL; @@ -1451,7 +1482,6 @@ int dev_set_alias(struct net_device *dev, const char *alias, size_t len) return len; } -EXPORT_SYMBOL(dev_set_alias); /** * dev_get_alias - get ifalias of a device @@ -1597,6 +1627,8 @@ static int __dev_open(struct net_device *dev, struct netlink_ext_ack *extack) set_bit(__LINK_STATE_START, &dev->state); + netdev_ops_assert_locked(dev); + if (ops->ndo_validate_addr) ret = ops->ndo_validate_addr(dev); @@ -1617,20 +1649,7 @@ static int __dev_open(struct net_device *dev, struct netlink_ext_ack *extack) return ret; } -/** - * dev_open - prepare an interface for use. - * @dev: device to open - * @extack: netlink extended ack - * - * Takes a device from down to up state. The device's private open - * function is invoked and then the multicast lists are loaded. Finally - * the device is moved into the up state and a %NETDEV_UP message is - * sent to the netdev notifier chain. - * - * Calling this function on an active interface is a nop. On a failure - * a negative errno code is returned. - */ -int dev_open(struct net_device *dev, struct netlink_ext_ack *extack) +int netif_open(struct net_device *dev, struct netlink_ext_ack *extack) { int ret; @@ -1646,7 +1665,6 @@ int dev_open(struct net_device *dev, struct netlink_ext_ack *extack) return ret; } -EXPORT_SYMBOL(dev_open); static void __dev_close_many(struct list_head *head) { @@ -1684,6 +1702,9 @@ static void __dev_close_many(struct list_head *head) * We allow it to be called even after a DETACH hot-plug * event. */ + + netdev_ops_assert_locked(dev); + if (ops->ndo_stop) ops->ndo_stop(dev); @@ -1721,16 +1742,7 @@ void dev_close_many(struct list_head *head, bool unlink) } EXPORT_SYMBOL(dev_close_many); -/** - * dev_close - shutdown an interface. - * @dev: device to shutdown - * - * This function moves an active device into down state. A - * %NETDEV_GOING_DOWN is sent to the netdev notifier chain. The device - * is then deactivated and finally a %NETDEV_DOWN is sent to the notifier - * chain. - */ -void dev_close(struct net_device *dev) +void netif_close(struct net_device *dev) { if (dev->flags & IFF_UP) { LIST_HEAD(single); @@ -1740,18 +1752,9 @@ void dev_close(struct net_device *dev) list_del(&single); } } -EXPORT_SYMBOL(dev_close); +EXPORT_SYMBOL(netif_close); - -/** - * dev_disable_lro - disable Large Receive Offload on a device - * @dev: device - * - * Disable Large Receive Offload (LRO) on a net device. Must be - * called under RTNL. This is needed if received packets may be - * forwarded to another interface. - */ -void dev_disable_lro(struct net_device *dev) +void netif_disable_lro(struct net_device *dev) { struct net_device *lower_dev; struct list_head *iter; @@ -1762,10 +1765,13 @@ void dev_disable_lro(struct net_device *dev) if (unlikely(dev->features & NETIF_F_LRO)) netdev_WARN(dev, "failed to disable LRO!\n"); - netdev_for_each_lower_dev(dev, lower_dev, iter) - dev_disable_lro(lower_dev); + netdev_for_each_lower_dev(dev, lower_dev, iter) { + netdev_lock_ops(lower_dev); + netif_disable_lro(lower_dev); + netdev_unlock_ops(lower_dev); + } } -EXPORT_SYMBOL(dev_disable_lro); +EXPORT_IPV6_MOD(netif_disable_lro); /** * dev_disable_gro_hw - disable HW Generic Receive Offload on a device @@ -1853,7 +1859,9 @@ static int call_netdevice_register_net_notifiers(struct notifier_block *nb, int err; for_each_netdev(net, dev) { + netdev_lock_ops(dev); err = call_netdevice_register_notifiers(nb, dev); + netdev_unlock_ops(dev); if (err) goto rollback; } @@ -2070,20 +2078,55 @@ static void __move_netdevice_notifier_net(struct net *src_net, __register_netdevice_notifier_net(dst_net, nb, true); } +static void rtnl_net_dev_lock(struct net_device *dev) +{ + bool again; + + do { + struct net *net; + + again = false; + + /* netns might be being dismantled. */ + rcu_read_lock(); + net = dev_net_rcu(dev); + net_passive_inc(net); + rcu_read_unlock(); + + rtnl_net_lock(net); + +#ifdef CONFIG_NET_NS + /* dev might have been moved to another netns. */ + if (!net_eq(net, rcu_access_pointer(dev->nd_net.net))) { + rtnl_net_unlock(net); + net_passive_dec(net); + again = true; + } +#endif + } while (again); +} + +static void rtnl_net_dev_unlock(struct net_device *dev) +{ + struct net *net = dev_net(dev); + + rtnl_net_unlock(net); + net_passive_dec(net); +} + int register_netdevice_notifier_dev_net(struct net_device *dev, struct notifier_block *nb, struct netdev_net_notifier *nn) { - struct net *net = dev_net(dev); int err; - rtnl_net_lock(net); - err = __register_netdevice_notifier_net(net, nb, false); + rtnl_net_dev_lock(dev); + err = __register_netdevice_notifier_net(dev_net(dev), nb, false); if (!err) { nn->nb = nb; list_add(&nn->list, &dev->net_notifier_list); } - rtnl_net_unlock(net); + rtnl_net_dev_unlock(dev); return err; } @@ -2093,13 +2136,12 @@ int unregister_netdevice_notifier_dev_net(struct net_device *dev, struct notifier_block *nb, struct netdev_net_notifier *nn) { - struct net *net = dev_net(dev); int err; - rtnl_net_lock(net); + rtnl_net_dev_lock(dev); list_del(&nn->list); - err = __unregister_netdevice_notifier_net(net, nb); - rtnl_net_unlock(net); + err = __unregister_netdevice_notifier_net(dev_net(dev), nb); + rtnl_net_dev_unlock(dev); return err; } @@ -2416,16 +2458,21 @@ static inline bool skb_loop_sk(struct packet_type *ptype, struct sk_buff *skb) } /** - * dev_nit_active - return true if any network interface taps are in use + * dev_nit_active_rcu - return true if any network interface taps are in use + * + * The caller must hold the RCU lock * * @dev: network device to check for the presence of taps */ -bool dev_nit_active(struct net_device *dev) +bool dev_nit_active_rcu(const struct net_device *dev) { - return !list_empty(&net_hotdata.ptype_all) || + /* Callers may hold either RCU or RCU BH lock */ + WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_bh_held()); + + return !list_empty(&dev_net(dev)->ptype_all) || !list_empty(&dev->ptype_all); } -EXPORT_SYMBOL_GPL(dev_nit_active); +EXPORT_SYMBOL_GPL(dev_nit_active_rcu); /* * Support routine. Sends outgoing frames to any network @@ -2434,11 +2481,12 @@ EXPORT_SYMBOL_GPL(dev_nit_active); void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev) { - struct list_head *ptype_list = &net_hotdata.ptype_all; struct packet_type *ptype, *pt_prev = NULL; + struct list_head *ptype_list; struct sk_buff *skb2 = NULL; rcu_read_lock(); + ptype_list = &dev_net_rcu(dev)->ptype_all; again: list_for_each_entry_rcu(ptype, ptype_list, list) { if (READ_ONCE(ptype->ignore_outgoing)) @@ -2482,7 +2530,7 @@ again: pt_prev = ptype; } - if (ptype_list == &net_hotdata.ptype_all) { + if (ptype_list != &dev->ptype_all) { ptype_list = &dev->ptype_all; goto again; } @@ -3085,6 +3133,7 @@ int netif_set_real_num_tx_queues(struct net_device *dev, unsigned int txq) if (dev->reg_state == NETREG_REGISTERED || dev->reg_state == NETREG_UNREGISTERING) { ASSERT_RTNL(); + netdev_ops_assert_locked(dev); rc = netdev_queue_update_kobjects(dev, dev->real_num_tx_queues, txq); @@ -3115,7 +3164,6 @@ int netif_set_real_num_tx_queues(struct net_device *dev, unsigned int txq) } EXPORT_SYMBOL(netif_set_real_num_tx_queues); -#ifdef CONFIG_SYSFS /** * netif_set_real_num_rx_queues - set actual number of RX queues used * @dev: Network device @@ -3135,6 +3183,7 @@ int netif_set_real_num_rx_queues(struct net_device *dev, unsigned int rxq) if (dev->reg_state == NETREG_REGISTERED) { ASSERT_RTNL(); + netdev_ops_assert_locked(dev); rc = net_rx_queue_update_kobjects(dev, dev->real_num_rx_queues, rxq); @@ -3146,7 +3195,6 @@ int netif_set_real_num_rx_queues(struct net_device *dev, unsigned int rxq) return 0; } EXPORT_SYMBOL(netif_set_real_num_rx_queues); -#endif /** * netif_set_real_num_queues - set actual number of RX and TX queues used @@ -3727,7 +3775,7 @@ static int xmit_one(struct sk_buff *skb, struct net_device *dev, unsigned int len; int rc; - if (dev_nit_active(dev)) + if (dev_nit_active_rcu(dev)) dev_queue_xmit_nit(skb, dev); len = skb->len; @@ -3807,6 +3855,9 @@ static struct sk_buff *validate_xmit_skb(struct sk_buff *skb, struct net_device { netdev_features_t features; + if (!skb_frags_readable(skb)) + goto out_kfree_skb; + features = netif_skb_features(skb); skb = validate_xmit_vlan(skb, features); if (unlikely(!skb)) @@ -4500,7 +4551,8 @@ int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev) skb_reset_mac_header(skb); skb_assert_len(skb); - if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_SCHED_TSTAMP)) + if (unlikely(skb_shinfo(skb)->tx_flags & + (SKBTX_SCHED_TSTAMP | SKBTX_BPF))) __skb_tstamp_tx(skb, NULL, NULL, skb->sk, SCM_TSTAMP_SCHED); /* Disable soft irqs for various locks below. Also @@ -4692,7 +4744,7 @@ use_local_napi: * we have to raise NET_RX_SOFTIRQ. */ if (!sd->in_net_rx_action) - __raise_softirq_irqoff(NET_RX_SOFTIRQ); + raise_softirq_irqoff(NET_RX_SOFTIRQ); } #ifdef CONFIG_RPS @@ -4702,6 +4754,11 @@ EXPORT_SYMBOL(rps_needed); struct static_key_false rfs_needed __read_mostly; EXPORT_SYMBOL(rfs_needed); +static u32 rfs_slot(u32 hash, const struct rps_dev_flow_table *flow_table) +{ + return hash_32(hash, flow_table->log); +} + static struct rps_dev_flow * set_rps_cpu(struct net_device *dev, struct sk_buff *skb, struct rps_dev_flow *rflow, u16 next_cpu) @@ -4728,7 +4785,7 @@ set_rps_cpu(struct net_device *dev, struct sk_buff *skb, flow_table = rcu_dereference(rxqueue->rps_flow_table); if (!flow_table) goto out; - flow_id = skb_get_hash(skb) & flow_table->mask; + flow_id = rfs_slot(skb_get_hash(skb), flow_table); rc = dev->netdev_ops->ndo_rx_flow_steer(dev, skb, rxq_index, flow_id); if (rc < 0) @@ -4807,7 +4864,7 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb, /* OK, now we know there is a match, * we can look at the local (per receive queue) flow table */ - rflow = &flow_table->flows[hash & flow_table->mask]; + rflow = &flow_table->flows[rfs_slot(hash, flow_table)]; tcpu = rflow->cpu; /* @@ -4874,13 +4931,13 @@ bool rps_may_expire_flow(struct net_device *dev, u16 rxq_index, rcu_read_lock(); flow_table = rcu_dereference(rxqueue->rps_flow_table); - if (flow_table && flow_id <= flow_table->mask) { + if (flow_table && flow_id < (1UL << flow_table->log)) { rflow = &flow_table->flows[flow_id]; cpu = READ_ONCE(rflow->cpu); if (READ_ONCE(rflow->filter) == filter_id && cpu < nr_cpu_ids && ((int)(READ_ONCE(per_cpu(softnet_data, cpu).input_queue_head) - READ_ONCE(rflow->last_qtail)) < - (int)(10 * flow_table->mask))) + (int)(10 << flow_table->log))) expire = false; } rcu_read_unlock(); @@ -5667,7 +5724,8 @@ another_round: if (pfmemalloc) goto skip_taps; - list_for_each_entry_rcu(ptype, &net_hotdata.ptype_all, list) { + list_for_each_entry_rcu(ptype, &dev_net_rcu(skb->dev)->ptype_all, + list) { if (pt_prev) ret = deliver_skb(skb, pt_prev, orig_dev); pt_prev = ptype; @@ -5779,6 +5837,14 @@ check_vlan_id: deliver_ptype_list_skb(skb, &pt_prev, orig_dev, type, &ptype_base[ntohs(type) & PTYPE_HASH_MASK]); + + /* orig_dev and skb->dev could belong to different netns; + * Even in such case we need to traverse only the list + * coming from skb->dev, as the ptype owner (packet socket) + * will use dev_net(skb->dev) to do namespace filtering. + */ + deliver_ptype_list_skb(skb, &pt_prev, orig_dev, type, + &dev_net_rcu(skb->dev)->ptype_specific); } deliver_ptype_list_skb(skb, &pt_prev, orig_dev, type, @@ -5989,7 +6055,7 @@ static int generic_xdp_install(struct net_device *dev, struct netdev_bpf *xdp) static_branch_dec(&generic_xdp_needed_key); } else if (new && !old) { static_branch_inc(&generic_xdp_needed_key); - dev_disable_lro(dev); + netif_disable_lro(dev); dev_disable_gro_hw(dev); } break; @@ -6119,16 +6185,18 @@ EXPORT_SYMBOL(netif_receive_skb_list); static void flush_backlog(struct work_struct *work) { struct sk_buff *skb, *tmp; + struct sk_buff_head list; struct softnet_data *sd; + __skb_queue_head_init(&list); local_bh_disable(); sd = this_cpu_ptr(&softnet_data); backlog_lock_irq_disable(sd); skb_queue_walk_safe(&sd->input_pkt_queue, skb, tmp) { - if (skb->dev->reg_state == NETREG_UNREGISTERING) { + if (READ_ONCE(skb->dev->reg_state) == NETREG_UNREGISTERING) { __skb_unlink(skb, &sd->input_pkt_queue); - dev_kfree_skb_irq(skb); + __skb_queue_tail(&list, skb); rps_input_queue_head_incr(sd); } } @@ -6136,14 +6204,16 @@ static void flush_backlog(struct work_struct *work) local_lock_nested_bh(&softnet_data.process_queue_bh_lock); skb_queue_walk_safe(&sd->process_queue, skb, tmp) { - if (skb->dev->reg_state == NETREG_UNREGISTERING) { + if (READ_ONCE(skb->dev->reg_state) == NETREG_UNREGISTERING) { __skb_unlink(skb, &sd->process_queue); - kfree_skb(skb); + __skb_queue_tail(&list, skb); rps_input_queue_head_incr(sd); } } local_unlock_nested_bh(&softnet_data.process_queue_bh_lock); local_bh_enable(); + + __skb_queue_purge_reason(&list, SKB_DROP_REASON_DEV_READY); } static bool flush_required(int cpu) @@ -6407,7 +6477,7 @@ bool napi_complete_done(struct napi_struct *n, int work_done) return false; if (work_done) { - if (n->gro_bitmask) + if (n->gro.bitmask) timeout = napi_get_gro_flush_timeout(n); n->defer_hard_irqs_count = napi_get_defer_hard_irqs(n); } @@ -6417,15 +6487,14 @@ bool napi_complete_done(struct napi_struct *n, int work_done) if (timeout) ret = false; } - if (n->gro_bitmask) { - /* When the NAPI instance uses a timeout and keeps postponing - * it, we need to bound somehow the time packets are kept in - * the GRO layer - */ - napi_gro_flush(n, !!timeout); - } - gro_normal_list(n); + /* + * When the NAPI instance uses a timeout and keeps postponing + * it, we need to bound somehow the time packets are kept in + * the GRO layer. + */ + gro_flush(&n->gro, !!timeout); + gro_normal_list(&n->gro); if (unlikely(!list_empty(&n->poll_list))) { /* If n->poll_list is not empty, we need to mask irqs */ @@ -6489,19 +6558,15 @@ static void skb_defer_free_flush(struct softnet_data *sd) static void __busy_poll_stop(struct napi_struct *napi, bool skip_schedule) { if (!skip_schedule) { - gro_normal_list(napi); + gro_normal_list(&napi->gro); __napi_schedule(napi); return; } - if (napi->gro_bitmask) { - /* flush too old packets - * If HZ < 1000, flush all packets. - */ - napi_gro_flush(napi, HZ >= 1000); - } + /* Flush too old packets. If HZ < 1000, flush all packets */ + gro_flush(&napi->gro, HZ >= 1000); + gro_normal_list(&napi->gro); - gro_normal_list(napi); clear_bit(NAPI_STATE_SCHED, &napi->state); } @@ -6608,7 +6673,7 @@ restart: } work = napi_poll(napi, budget); trace_napi_poll(napi, work, budget); - gro_normal_list(napi); + gro_normal_list(&napi->gro); count: if (work > 0) __NET_ADD_STATS(dev_net(napi->dev), @@ -6708,6 +6773,8 @@ void napi_resume_irqs(unsigned int napi_id) static void __napi_hash_add_with_id(struct napi_struct *napi, unsigned int napi_id) { + napi->gro.cached_napi_id = napi_id; + WRITE_ONCE(napi->napi_id, napi_id); hlist_add_head_rcu(&napi->napi_hash_node, &napi_hash[napi->napi_id % HASH_SIZE(napi_hash)]); @@ -6735,7 +6802,7 @@ static void napi_hash_add(struct napi_struct *napi) /* 0..NR_CPUS range is reserved for sender_cpu use */ do { - if (unlikely(++napi_gen_id < MIN_NAPI_ID)) + if (unlikely(!napi_id_valid(++napi_gen_id))) napi_gen_id = MIN_NAPI_ID; } while (napi_by_id(napi_gen_id)); @@ -6776,17 +6843,6 @@ static enum hrtimer_restart napi_watchdog(struct hrtimer *timer) return HRTIMER_NORESTART; } -static void init_gro_hash(struct napi_struct *napi) -{ - int i; - - for (i = 0; i < GRO_HASH_BUCKETS; i++) { - INIT_LIST_HEAD(&napi->gro_hash[i].list); - napi->gro_hash[i].count = 0; - } - napi->gro_bitmask = 0; -} - int dev_set_threaded(struct net_device *dev, bool threaded) { struct napi_struct *napi; @@ -6848,8 +6904,7 @@ void netif_queue_set_napi(struct net_device *dev, unsigned int queue_index, if (WARN_ON_ONCE(napi && !napi->dev)) return; - if (dev->reg_state >= NETREG_REGISTERED) - ASSERT_RTNL(); + netdev_ops_assert_locked_or_invisible(dev); switch (type) { case NETDEV_QUEUE_TYPE_RX: @@ -6866,11 +6921,175 @@ void netif_queue_set_napi(struct net_device *dev, unsigned int queue_index, } EXPORT_SYMBOL(netif_queue_set_napi); +static void +netif_napi_irq_notify(struct irq_affinity_notify *notify, + const cpumask_t *mask) +{ + struct napi_struct *napi = + container_of(notify, struct napi_struct, notify); +#ifdef CONFIG_RFS_ACCEL + struct cpu_rmap *rmap = napi->dev->rx_cpu_rmap; + int err; +#endif + + if (napi->config && napi->dev->irq_affinity_auto) + cpumask_copy(&napi->config->affinity_mask, mask); + +#ifdef CONFIG_RFS_ACCEL + if (napi->dev->rx_cpu_rmap_auto) { + err = cpu_rmap_update(rmap, napi->napi_rmap_idx, mask); + if (err) + netdev_warn(napi->dev, "RMAP update failed (%d)\n", + err); + } +#endif +} + +#ifdef CONFIG_RFS_ACCEL +static void netif_napi_affinity_release(struct kref *ref) +{ + struct napi_struct *napi = + container_of(ref, struct napi_struct, notify.kref); + struct cpu_rmap *rmap = napi->dev->rx_cpu_rmap; + + netdev_assert_locked(napi->dev); + WARN_ON(test_and_clear_bit(NAPI_STATE_HAS_NOTIFIER, + &napi->state)); + + if (!napi->dev->rx_cpu_rmap_auto) + return; + rmap->obj[napi->napi_rmap_idx] = NULL; + napi->napi_rmap_idx = -1; + cpu_rmap_put(rmap); +} + +int netif_enable_cpu_rmap(struct net_device *dev, unsigned int num_irqs) +{ + if (dev->rx_cpu_rmap_auto) + return 0; + + dev->rx_cpu_rmap = alloc_irq_cpu_rmap(num_irqs); + if (!dev->rx_cpu_rmap) + return -ENOMEM; + + dev->rx_cpu_rmap_auto = true; + return 0; +} +EXPORT_SYMBOL(netif_enable_cpu_rmap); + +static void netif_del_cpu_rmap(struct net_device *dev) +{ + struct cpu_rmap *rmap = dev->rx_cpu_rmap; + + if (!dev->rx_cpu_rmap_auto) + return; + + /* Free the rmap */ + cpu_rmap_put(rmap); + dev->rx_cpu_rmap = NULL; + dev->rx_cpu_rmap_auto = false; +} + +#else +static void netif_napi_affinity_release(struct kref *ref) +{ +} + +int netif_enable_cpu_rmap(struct net_device *dev, unsigned int num_irqs) +{ + return 0; +} +EXPORT_SYMBOL(netif_enable_cpu_rmap); + +static void netif_del_cpu_rmap(struct net_device *dev) +{ +} +#endif + +void netif_set_affinity_auto(struct net_device *dev) +{ + unsigned int i, maxqs, numa; + + maxqs = max(dev->num_tx_queues, dev->num_rx_queues); + numa = dev_to_node(&dev->dev); + + for (i = 0; i < maxqs; i++) + cpumask_set_cpu(cpumask_local_spread(i, numa), + &dev->napi_config[i].affinity_mask); + + dev->irq_affinity_auto = true; +} +EXPORT_SYMBOL(netif_set_affinity_auto); + +void netif_napi_set_irq_locked(struct napi_struct *napi, int irq) +{ + int rc; + + netdev_assert_locked_or_invisible(napi->dev); + + if (napi->irq == irq) + return; + + /* Remove existing resources */ + if (test_and_clear_bit(NAPI_STATE_HAS_NOTIFIER, &napi->state)) + irq_set_affinity_notifier(napi->irq, NULL); + + napi->irq = irq; + if (irq < 0 || + (!napi->dev->rx_cpu_rmap_auto && !napi->dev->irq_affinity_auto)) + return; + + /* Abort for buggy drivers */ + if (napi->dev->irq_affinity_auto && WARN_ON_ONCE(!napi->config)) + return; + +#ifdef CONFIG_RFS_ACCEL + if (napi->dev->rx_cpu_rmap_auto) { + rc = cpu_rmap_add(napi->dev->rx_cpu_rmap, napi); + if (rc < 0) + return; + + cpu_rmap_get(napi->dev->rx_cpu_rmap); + napi->napi_rmap_idx = rc; + } +#endif + + /* Use core IRQ notifier */ + napi->notify.notify = netif_napi_irq_notify; + napi->notify.release = netif_napi_affinity_release; + rc = irq_set_affinity_notifier(irq, &napi->notify); + if (rc) { + netdev_warn(napi->dev, "Unable to set IRQ notifier (%d)\n", + rc); + goto put_rmap; + } + + set_bit(NAPI_STATE_HAS_NOTIFIER, &napi->state); + return; + +put_rmap: +#ifdef CONFIG_RFS_ACCEL + if (napi->dev->rx_cpu_rmap_auto) { + napi->dev->rx_cpu_rmap->obj[napi->napi_rmap_idx] = NULL; + cpu_rmap_put(napi->dev->rx_cpu_rmap); + napi->napi_rmap_idx = -1; + } +#endif + napi->notify.notify = NULL; + napi->notify.release = NULL; +} +EXPORT_SYMBOL(netif_napi_set_irq_locked); + static void napi_restore_config(struct napi_struct *n) { n->defer_hard_irqs = n->config->defer_hard_irqs; n->gro_flush_timeout = n->config->gro_flush_timeout; n->irq_suspend_timeout = n->config->irq_suspend_timeout; + + if (n->dev->irq_affinity_auto && + test_bit(NAPI_STATE_HAS_NOTIFIER, &n->state)) + irq_set_affinity(n->irq, &n->config->affinity_mask); + /* a NAPI ID might be stored in the config, if so use it. if not, use * napi_hash_add to generate one for us. */ @@ -6906,7 +7125,7 @@ netif_napi_dev_list_add(struct net_device *dev, struct napi_struct *napi) higher = &dev->napi_list; list_for_each_entry(pos, &dev->napi_list, dev_list) { - if (pos->napi_id >= MIN_NAPI_ID) + if (napi_id_valid(pos->napi_id)) pos_id = pos->napi_id; else if (pos->config) pos_id = pos->config->napi_id; @@ -6920,6 +7139,23 @@ netif_napi_dev_list_add(struct net_device *dev, struct napi_struct *napi) list_add_rcu(&napi->dev_list, higher); /* adds after higher */ } +/* Double check that napi_get_frags() allocates skbs with + * skb->head being backed by slab, not a page fragment. + * This is to make sure bug fixed in 3226b158e67c + * ("net: avoid 32 x truesize under-estimation for tiny skbs") + * does not accidentally come back. + */ +static void napi_get_frags_check(struct napi_struct *napi) +{ + struct sk_buff *skb; + + local_bh_disable(); + skb = napi_get_frags(napi); + WARN_ON_ONCE(skb && skb->head_frag); + napi_free_frags(napi); + local_bh_enable(); +} + void netif_napi_add_weight_locked(struct net_device *dev, struct napi_struct *napi, int (*poll)(struct napi_struct *, int), @@ -6931,12 +7167,9 @@ void netif_napi_add_weight_locked(struct net_device *dev, INIT_LIST_HEAD(&napi->poll_list); INIT_HLIST_NODE(&napi->napi_hash_node); - hrtimer_init(&napi->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED); - napi->timer.function = napi_watchdog; - init_gro_hash(napi); + hrtimer_setup(&napi->timer, napi_watchdog, CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED); + gro_init(&napi->gro); napi->skb = NULL; - INIT_LIST_HEAD(&napi->rx_list); - napi->rx_count = 0; napi->poll = poll; if (weight > NAPI_POLL_WEIGHT) netdev_err_once(dev, "%s() called with weight %d\n", __func__, @@ -7050,19 +7283,6 @@ void napi_enable(struct napi_struct *n) } EXPORT_SYMBOL(napi_enable); -static void flush_gro_hash(struct napi_struct *napi) -{ - int i; - - for (i = 0; i < GRO_HASH_BUCKETS; i++) { - struct sk_buff *skb, *n; - - list_for_each_entry_safe(skb, n, &napi->gro_hash[i].list, list) - kfree_skb(skb); - napi->gro_hash[i].count = 0; - } -} - /* Must be called in process context */ void __netif_napi_del_locked(struct napi_struct *napi) { @@ -7071,6 +7291,12 @@ void __netif_napi_del_locked(struct napi_struct *napi) if (!test_and_clear_bit(NAPI_STATE_LISTED, &napi->state)) return; + /* Make sure NAPI is disabled (or was never enabled). */ + WARN_ON(!test_bit(NAPI_STATE_SCHED, &napi->state)); + + if (test_and_clear_bit(NAPI_STATE_HAS_NOTIFIER, &napi->state)) + irq_set_affinity_notifier(napi->irq, NULL); + if (napi->config) { napi->index = -1; napi->config = NULL; @@ -7079,8 +7305,7 @@ void __netif_napi_del_locked(struct napi_struct *napi) list_del_rcu(&napi->dev_list); napi_free_frags(napi); - flush_gro_hash(napi); - napi->gro_bitmask = 0; + gro_cleanup(&napi->gro); if (napi->thread) { kthread_stop(napi->thread); @@ -7139,14 +7364,9 @@ static int __napi_poll(struct napi_struct *n, bool *repoll) return work; } - if (n->gro_bitmask) { - /* flush too old packets - * If HZ < 1000, flush all packets. - */ - napi_gro_flush(n, HZ >= 1000); - } - - gro_normal_list(n); + /* Flush too old packets. If HZ < 1000, flush all packets */ + gro_flush(&n->gro, HZ >= 1000); + gro_normal_list(&n->gro); /* Some drivers may have called napi_schedule * prior to exhausting their budget. @@ -9005,7 +9225,7 @@ int dev_set_promiscuity(struct net_device *dev, int inc) } EXPORT_SYMBOL(dev_set_promiscuity); -static int __dev_set_allmulti(struct net_device *dev, int inc, bool notify) +int netif_set_allmulti(struct net_device *dev, int inc, bool notify) { unsigned int old_flags = dev->flags, old_gflags = dev->gflags; unsigned int allmulti, flags; @@ -9040,25 +9260,6 @@ static int __dev_set_allmulti(struct net_device *dev, int inc, bool notify) return 0; } -/** - * dev_set_allmulti - update allmulti count on a device - * @dev: device - * @inc: modifier - * - * Add or remove reception of all multicast frames to a device. While the - * count in the device remains above zero the interface remains listening - * to all interfaces. Once it hits zero the device reverts back to normal - * filtering operation. A negative @inc value is used to drop the counter - * when releasing a resource needing all multicasts. - * Return 0 if successful or a negative errno code on error. - */ - -int dev_set_allmulti(struct net_device *dev, int inc) -{ - return __dev_set_allmulti(dev, inc, true); -} -EXPORT_SYMBOL(dev_set_allmulti); - /* * Upload unicast and multicast address lists to device and * configure RX filtering. When the device doesn't support unicast @@ -9174,7 +9375,7 @@ int __dev_change_flags(struct net_device *dev, unsigned int flags, if ((flags ^ dev->gflags) & IFF_PROMISC) { int inc = (flags & IFF_PROMISC) ? 1 : -1; - unsigned int old_flags = dev->flags; + old_flags = dev->flags; dev->gflags ^= IFF_PROMISC; @@ -9191,7 +9392,7 @@ int __dev_change_flags(struct net_device *dev, unsigned int flags, int inc = (flags & IFF_ALLMULTI) ? 1 : -1; dev->gflags ^= IFF_ALLMULTI; - __dev_set_allmulti(dev, inc, false); + netif_set_allmulti(dev, inc, false); } return ret; @@ -9226,17 +9427,8 @@ void __dev_notify_flags(struct net_device *dev, unsigned int old_flags, } } -/** - * dev_change_flags - change device settings - * @dev: device - * @flags: device state flags - * @extack: netlink extended ack - * - * Change settings on device based state flags. The flags are - * in the userspace exported format. - */ -int dev_change_flags(struct net_device *dev, unsigned int flags, - struct netlink_ext_ack *extack) +int netif_change_flags(struct net_device *dev, unsigned int flags, + struct netlink_ext_ack *extack) { int ret; unsigned int changes, old_flags = dev->flags, old_gflags = dev->gflags; @@ -9249,7 +9441,6 @@ int dev_change_flags(struct net_device *dev, unsigned int flags, __dev_notify_flags(dev, old_flags, changes, 0, NULL); return ret; } -EXPORT_SYMBOL(dev_change_flags); int __dev_set_mtu(struct net_device *dev, int new_mtu) { @@ -9281,15 +9472,15 @@ int dev_validate_mtu(struct net_device *dev, int new_mtu, } /** - * dev_set_mtu_ext - Change maximum transfer unit + * netif_set_mtu_ext - Change maximum transfer unit * @dev: device * @new_mtu: new transfer unit * @extack: netlink extended ack * * Change the maximum transfer size of the network device. */ -int dev_set_mtu_ext(struct net_device *dev, int new_mtu, - struct netlink_ext_ack *extack) +int netif_set_mtu_ext(struct net_device *dev, int new_mtu, + struct netlink_ext_ack *extack) { int err, orig_mtu; @@ -9327,25 +9518,20 @@ int dev_set_mtu_ext(struct net_device *dev, int new_mtu, return err; } -int dev_set_mtu(struct net_device *dev, int new_mtu) +int netif_set_mtu(struct net_device *dev, int new_mtu) { struct netlink_ext_ack extack; int err; memset(&extack, 0, sizeof(extack)); - err = dev_set_mtu_ext(dev, new_mtu, &extack); + err = netif_set_mtu_ext(dev, new_mtu, &extack); if (err && extack._msg) net_err_ratelimited("%s: %s\n", dev->name, extack._msg); return err; } -EXPORT_SYMBOL(dev_set_mtu); +EXPORT_SYMBOL(netif_set_mtu); -/** - * dev_change_tx_queue_len - Change TX queue length of a netdevice - * @dev: device - * @new_len: new tx queue length - */ -int dev_change_tx_queue_len(struct net_device *dev, unsigned long new_len) +int netif_change_tx_queue_len(struct net_device *dev, unsigned long new_len) { unsigned int orig_len = dev->tx_queue_len; int res; @@ -9372,12 +9558,7 @@ err_rollback: return res; } -/** - * dev_set_group - Change group this device belongs to - * @dev: device - * @new_group: group this device should belong to - */ -void dev_set_group(struct net_device *dev, int new_group) +void netif_set_group(struct net_device *dev, int new_group) { dev->group = new_group; } @@ -9403,16 +9584,8 @@ int dev_pre_changeaddr_notify(struct net_device *dev, const char *addr, } EXPORT_SYMBOL(dev_pre_changeaddr_notify); -/** - * dev_set_mac_address - Change Media Access Control Address - * @dev: device - * @sa: new address - * @extack: netlink extended ack - * - * Change the hardware (MAC) address of the device - */ -int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa, - struct netlink_ext_ack *extack) +int netif_set_mac_address(struct net_device *dev, struct sockaddr *sa, + struct netlink_ext_ack *extack) { const struct net_device_ops *ops = dev->netdev_ops; int err; @@ -9436,22 +9609,9 @@ int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa, add_device_randomness(dev->dev_addr, dev->addr_len); return 0; } -EXPORT_SYMBOL(dev_set_mac_address); DECLARE_RWSEM(dev_addr_sem); -int dev_set_mac_address_user(struct net_device *dev, struct sockaddr *sa, - struct netlink_ext_ack *extack) -{ - int ret; - - down_write(&dev_addr_sem); - ret = dev_set_mac_address(dev, sa, extack); - up_write(&dev_addr_sem); - return ret; -} -EXPORT_SYMBOL(dev_set_mac_address_user); - int dev_get_mac_address(struct sockaddr *sa, struct net *net, char *dev_name) { size_t size = sizeof(sa->sa_data_min); @@ -9480,14 +9640,7 @@ unlock: } EXPORT_SYMBOL(dev_get_mac_address); -/** - * dev_change_carrier - Change device carrier - * @dev: device - * @new_carrier: new value - * - * Change device carrier - */ -int dev_change_carrier(struct net_device *dev, bool new_carrier) +int netif_change_carrier(struct net_device *dev, bool new_carrier) { const struct net_device_ops *ops = dev->netdev_ops; @@ -9598,13 +9751,7 @@ bool netdev_port_same_parent_id(struct net_device *a, struct net_device *b) } EXPORT_SYMBOL(netdev_port_same_parent_id); -/** - * dev_change_proto_down - set carrier according to proto_down. - * - * @dev: device - * @proto_down: new value - */ -int dev_change_proto_down(struct net_device *dev, bool proto_down) +int netif_change_proto_down(struct net_device *dev, bool proto_down) { if (!dev->change_proto_down) return -EOPNOTSUPP; @@ -9619,14 +9766,14 @@ int dev_change_proto_down(struct net_device *dev, bool proto_down) } /** - * dev_change_proto_down_reason - proto down reason + * netdev_change_proto_down_reason_locked - proto down reason * * @dev: device * @mask: proto down mask * @value: proto down value */ -void dev_change_proto_down_reason(struct net_device *dev, unsigned long mask, - u32 value) +void netdev_change_proto_down_reason_locked(struct net_device *dev, + unsigned long mask, u32 value) { u32 proto_down_reason; int b; @@ -9715,7 +9862,7 @@ u8 dev_xdp_sb_prog_count(struct net_device *dev) return count; } -int dev_xdp_propagate(struct net_device *dev, struct netdev_bpf *bpf) +int netif_xdp_propagate(struct net_device *dev, struct netdev_bpf *bpf) { if (!dev->netdev_ops->ndo_bpf) return -EOPNOTSUPP; @@ -9735,7 +9882,6 @@ int dev_xdp_propagate(struct net_device *dev, struct netdev_bpf *bpf) return dev->netdev_ops->ndo_bpf(dev, bpf); } -EXPORT_SYMBOL_GPL(dev_xdp_propagate); u32 dev_xdp_prog_id(struct net_device *dev, enum bpf_xdp_mode mode) { @@ -9765,6 +9911,8 @@ static int dev_xdp_install(struct net_device *dev, enum bpf_xdp_mode mode, struct netdev_bpf xdp; int err; + netdev_ops_assert_locked(dev); + if (dev->cfg->hds_config == ETHTOOL_TCP_DATA_SPLIT_ENABLED && prog && !prog->aux->xdp_has_frags) { NL_SET_ERR_MSG(extack, "unable to install XDP to device using tcp-data-split"); @@ -9997,7 +10145,9 @@ static void bpf_xdp_link_release(struct bpf_link *link) * already NULL, in which case link was already auto-detached */ if (xdp_link->dev) { + netdev_lock_ops(xdp_link->dev); WARN_ON(dev_xdp_detach_link(xdp_link->dev, NULL, xdp_link)); + netdev_unlock_ops(xdp_link->dev); xdp_link->dev = NULL; } @@ -10079,10 +10229,12 @@ static int bpf_xdp_link_update(struct bpf_link *link, struct bpf_prog *new_prog, goto out_unlock; } + netdev_lock_ops(xdp_link->dev); mode = dev_xdp_mode(xdp_link->dev, xdp_link->flags); bpf_op = dev_xdp_bpf_op(xdp_link->dev, mode); err = dev_xdp_install(xdp_link->dev, mode, bpf_op, NULL, xdp_link->flags, new_prog); + netdev_unlock_ops(xdp_link->dev); if (err) goto out_unlock; @@ -10135,7 +10287,9 @@ int bpf_xdp_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) goto unlock; } + netdev_lock_ops(dev); err = dev_xdp_attach_link(dev, &extack, link); + netdev_unlock_ops(dev); rtnl_unlock(); if (err) { @@ -10208,7 +10362,7 @@ u32 dev_get_min_mp_channel_count(const struct net_device *dev) { int i; - ASSERT_RTNL(); + netdev_ops_assert_locked(dev); for (i = dev->real_num_rx_queues - 1; i >= 0; i--) if (dev->_rx[i].mp_params.mp_priv) @@ -10434,6 +10588,7 @@ int __netdev_update_features(struct net_device *dev) int err = -1; ASSERT_RTNL(); + netdev_ops_assert_locked(dev); features = netdev_get_wanted_features(dev); @@ -10867,7 +11022,9 @@ int register_netdevice(struct net_device *dev) if (ret) goto err_uninit_notify; + netdev_lock_ops(dev); __netdev_update_features(dev); + netdev_unlock_ops(dev); /* * Default initial state at registry is that the @@ -10893,7 +11050,9 @@ int register_netdevice(struct net_device *dev) memcpy(dev->perm_addr, dev->dev_addr, dev->addr_len); /* Notify protocols, that a new device appeared. */ + netdev_lock_ops(dev); ret = call_netdevice_notifiers(NETDEV_REGISTER, dev); + netdev_unlock_ops(dev); ret = notifier_to_errno(ret); if (ret) { /* Expect explicit free_netdev() on failure */ @@ -11112,9 +11271,8 @@ void netdev_run_todo(void) list_replace_init(&net_unlink_list, &unlink_list); while (!list_empty(&unlink_list)) { - struct net_device *dev = list_first_entry(&unlink_list, - struct net_device, - unlink_list); + dev = list_first_entry(&unlink_list, struct net_device, + unlink_list); list_del_init(&dev->unlink_list); dev->nested_level = dev->lower_level - 1; } @@ -11286,6 +11444,20 @@ struct rtnl_link_stats64 *dev_get_stats(struct net_device *dev, const struct net_device_ops *ops = dev->netdev_ops; const struct net_device_core_stats __percpu *p; + /* + * IPv{4,6} and udp tunnels share common stat helpers and use + * different stat type (NETDEV_PCPU_STAT_TSTATS vs + * NETDEV_PCPU_STAT_DSTATS). Ensure the accounting is consistent. + */ + BUILD_BUG_ON(offsetof(struct pcpu_sw_netstats, rx_bytes) != + offsetof(struct pcpu_dstats, rx_bytes)); + BUILD_BUG_ON(offsetof(struct pcpu_sw_netstats, rx_packets) != + offsetof(struct pcpu_dstats, rx_packets)); + BUILD_BUG_ON(offsetof(struct pcpu_sw_netstats, tx_bytes) != + offsetof(struct pcpu_dstats, tx_bytes)); + BUILD_BUG_ON(offsetof(struct pcpu_sw_netstats, tx_packets) != + offsetof(struct pcpu_dstats, tx_packets)); + if (ops->ndo_get_stats64) { memset(storage, 0, sizeof(*storage)); ops->ndo_get_stats64(dev, storage); @@ -11610,6 +11782,8 @@ void free_netdev(struct net_device *dev) netdev_napi_exit(dev); + netif_del_cpu_rmap(dev); + ref_tracker_dir_exit(&dev->refcnt_tracker); #ifdef CONFIG_PCPU_DEV_REFCNT free_percpu(dev->pcpu_refcnt); @@ -11724,6 +11898,19 @@ void unregister_netdevice_queue(struct net_device *dev, struct list_head *head) } EXPORT_SYMBOL(unregister_netdevice_queue); +static void dev_memory_provider_uninstall(struct net_device *dev) +{ + unsigned int i; + + for (i = 0; i < dev->real_num_rx_queues; i++) { + struct netdev_rx_queue *rxq = &dev->_rx[i]; + struct pp_memory_provider_params *p = &rxq->mp_params; + + if (p->mp_ops && p->mp_ops->uninstall) + p->mp_ops->uninstall(rxq->mp_params.mp_priv, rxq); + } +} + void unregister_netdevice_many_notify(struct list_head *head, u32 portid, const struct nlmsghdr *nlh) { @@ -11755,11 +11942,14 @@ void unregister_netdevice_many_notify(struct list_head *head, } /* If device is running, close it first. */ - list_for_each_entry(dev, head, unreg_list) + list_for_each_entry(dev, head, unreg_list) { list_add_tail(&dev->close_list, &close_head); + netdev_lock_ops(dev); + } dev_close_many(&close_head, true); list_for_each_entry(dev, head, unreg_list) { + netdev_unlock_ops(dev); /* And unlink it from device chain. */ unlist_netdevice(dev); netdev_lock(dev); @@ -11776,9 +11966,11 @@ void unregister_netdevice_many_notify(struct list_head *head, /* Shutdown queueing discipline. */ dev_shutdown(dev); dev_tcx_uninstall(dev); + netdev_lock_ops(dev); dev_xdp_uninstall(dev); + dev_memory_provider_uninstall(dev); + netdev_unlock_ops(dev); bpf_dev_bound_netdev_unregister(dev); - dev_dmabuf_uninstall(dev); netdev_offload_xstats_disable_all(dev); @@ -11866,32 +12058,15 @@ EXPORT_SYMBOL(unregister_netdevice_many); */ void unregister_netdev(struct net_device *dev) { - struct net *net = dev_net(dev); - - rtnl_net_lock(net); + rtnl_net_dev_lock(dev); unregister_netdevice(dev); - rtnl_net_unlock(net); + rtnl_net_dev_unlock(dev); } EXPORT_SYMBOL(unregister_netdev); -/** - * __dev_change_net_namespace - move device to different nethost namespace - * @dev: device - * @net: network namespace - * @pat: If not NULL name pattern to try if the current device name - * is already taken in the destination network namespace. - * @new_ifindex: If not zero, specifies device index in the target - * namespace. - * - * This function shuts down a device interface and moves it - * to a new network namespace. On success 0 is returned, on - * a failure a netagive errno code is returned. - * - * Callers must hold the rtnl semaphore. - */ - int __dev_change_net_namespace(struct net_device *dev, struct net *net, - const char *pat, int new_ifindex) + const char *pat, int new_ifindex, + struct netlink_ext_ack *extack) { struct netdev_name_node *name_node; struct net *net_old = dev_net(dev); @@ -11902,12 +12077,16 @@ int __dev_change_net_namespace(struct net_device *dev, struct net *net, /* Don't allow namespace local devices to be moved. */ err = -EINVAL; - if (dev->netns_local) + if (dev->netns_immutable) { + NL_SET_ERR_MSG(extack, "The interface netns is immutable"); goto out; + } /* Ensure the device has been registered */ - if (dev->reg_state != NETREG_REGISTERED) + if (dev->reg_state != NETREG_REGISTERED) { + NL_SET_ERR_MSG(extack, "The interface isn't registered"); goto out; + } /* Get out if there is nothing todo */ err = 0; @@ -11920,30 +12099,49 @@ int __dev_change_net_namespace(struct net_device *dev, struct net *net, err = -EEXIST; if (netdev_name_in_use(net, dev->name)) { /* We get here if we can't use the current device name */ - if (!pat) + if (!pat) { + NL_SET_ERR_MSG(extack, + "An interface with the same name exists in the target netns"); goto out; + } err = dev_prep_valid_name(net, dev, pat, new_name, EEXIST); - if (err < 0) + if (err < 0) { + NL_SET_ERR_MSG_FMT(extack, + "Unable to use '%s' for the new interface name in the target netns", + pat); goto out; + } } /* Check that none of the altnames conflicts. */ err = -EEXIST; - netdev_for_each_altname(dev, name_node) - if (netdev_name_in_use(net, name_node->name)) + netdev_for_each_altname(dev, name_node) { + if (netdev_name_in_use(net, name_node->name)) { + NL_SET_ERR_MSG_FMT(extack, + "An interface with the altname %s exists in the target netns", + name_node->name); goto out; + } + } /* Check that new_ifindex isn't used yet. */ if (new_ifindex) { err = dev_index_reserve(net, new_ifindex); - if (err < 0) + if (err < 0) { + NL_SET_ERR_MSG_FMT(extack, + "The ifindex %d is not available in the target netns", + new_ifindex); goto out; + } } else { /* If there is an ifindex conflict assign a new one */ err = dev_index_reserve(net, dev->ifindex); if (err == -EBUSY) err = dev_index_reserve(net, 0); - if (err < 0) + if (err < 0) { + NL_SET_ERR_MSG(extack, + "Unable to allocate a new ifindex in the target netns"); goto out; + } new_ifindex = err; } @@ -11951,11 +12149,12 @@ int __dev_change_net_namespace(struct net_device *dev, struct net *net, * And now a mini version of register_netdevice unregister_netdevice. */ + netdev_lock_ops(dev); /* If device is running close it first. */ - dev_close(dev); - + netif_close(dev); /* And unlink it from device chain */ unlist_netdevice(dev); + netdev_unlock_ops(dev); synchronize_net(); @@ -12017,11 +12216,12 @@ int __dev_change_net_namespace(struct net_device *dev, struct net *net, err = netdev_change_owner(dev, net_old, net); WARN_ON(err); + netdev_lock_ops(dev); /* Add the device back in the hashes */ list_netdevice(dev); - /* Notify protocols, that a new device appeared. */ call_netdevice_notifiers(NETDEV_REGISTER, dev); + netdev_unlock_ops(dev); /* * Prevent userspace races by waiting until the network @@ -12034,7 +12234,6 @@ int __dev_change_net_namespace(struct net_device *dev, struct net *net, out: return err; } -EXPORT_SYMBOL_GPL(__dev_change_net_namespace); static int dev_cpu_dead(unsigned int oldcpu) { @@ -12149,7 +12348,7 @@ static struct hlist_head * __net_init netdev_create_hash(void) static int __net_init netdev_init(struct net *net) { BUILD_BUG_ON(GRO_HASH_BUCKETS > - 8 * sizeof_field(struct napi_struct, gro_bitmask)); + BITS_PER_BYTE * sizeof_field(struct gro_node, bitmask)); INIT_LIST_HEAD(&net->dev_base_head); @@ -12284,7 +12483,7 @@ static void __net_exit default_device_exit_net(struct net *net) char fb_name[IFNAMSIZ]; /* Ignore unmoveable devices (i.e. loopback) */ - if (dev->netns_local) + if (dev->netns_immutable) continue; /* Leave virtual devices for the generic cleanup */ @@ -12514,7 +12713,7 @@ static int __init net_dev_init(void) INIT_CSD(&sd->defer_csd, trigger_rx_softirq, sd); spin_lock_init(&sd->defer_lock); - init_gro_hash(&sd->backlog); + gro_init(&sd->backlog.gro); sd->backlog.poll = process_backlog; sd->backlog.weight = weight_p; INIT_LIST_HEAD(&sd->backlog.poll_list); diff --git a/net/core/dev.h b/net/core/dev.h index a5b166bbd169..7ee203395d8e 100644 --- a/net/core/dev.h +++ b/net/core/dev.h @@ -6,6 +6,7 @@ #include <linux/types.h> #include <linux/rwsem.h> #include <linux/netdevice.h> +#include <net/netdev_lock.h> struct net; struct netlink_ext_ack; @@ -85,6 +86,7 @@ struct netdev_name_node { }; int netdev_get_name(struct net *net, char *name, int ifindex); +int netif_change_name(struct net_device *dev, const char *newname); int dev_change_name(struct net_device *dev, const char *newname); #define netdev_for_each_altname(dev, namenode) \ @@ -98,24 +100,28 @@ int netdev_name_node_alt_destroy(struct net_device *dev, const char *name); int dev_validate_mtu(struct net_device *dev, int mtu, struct netlink_ext_ack *extack); -int dev_set_mtu_ext(struct net_device *dev, int mtu, - struct netlink_ext_ack *extack); +int netif_set_mtu_ext(struct net_device *dev, int new_mtu, + struct netlink_ext_ack *extack); int dev_get_phys_port_id(struct net_device *dev, struct netdev_phys_item_id *ppid); int dev_get_phys_port_name(struct net_device *dev, char *name, size_t len); +int netif_change_proto_down(struct net_device *dev, bool proto_down); int dev_change_proto_down(struct net_device *dev, bool proto_down); -void dev_change_proto_down_reason(struct net_device *dev, unsigned long mask, - u32 value); +void netdev_change_proto_down_reason_locked(struct net_device *dev, + unsigned long mask, u32 value); typedef int (*bpf_op_t)(struct net_device *dev, struct netdev_bpf *bpf); int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack, int fd, int expected_fd, u32 flags); +int netif_change_tx_queue_len(struct net_device *dev, unsigned long new_len); int dev_change_tx_queue_len(struct net_device *dev, unsigned long new_len); +void netif_set_group(struct net_device *dev, int new_group); void dev_set_group(struct net_device *dev, int new_group); +int netif_change_carrier(struct net_device *dev, bool new_carrier); int dev_change_carrier(struct net_device *dev, bool new_carrier); void __dev_set_rx_mode(struct net_device *dev); @@ -134,9 +140,11 @@ static inline void netif_set_up(struct net_device *dev, bool value) else dev->flags &= ~IFF_UP; - netdev_lock(dev); + if (!netdev_need_ops_lock(dev)) + netdev_lock(dev); dev->up = value; - netdev_unlock(dev); + if (!netdev_need_ops_lock(dev)) + netdev_unlock(dev); } static inline void netif_set_gso_max_size(struct net_device *dev, @@ -299,6 +307,18 @@ void xdp_do_check_flushed(struct napi_struct *napi); static inline void xdp_do_check_flushed(struct napi_struct *napi) { } #endif +/* Best effort check that NAPI is not idle (can't be scheduled to run) */ +static inline void napi_assert_will_not_race(const struct napi_struct *napi) +{ + /* uninitialized instance, can't race */ + if (!napi->poll_list.next) + return; + + /* SCHED bit is set on disabled instances */ + WARN_ON(!test_bit(NAPI_STATE_SCHED, &napi->state)); + WARN_ON(READ_ONCE(napi->list_owner) != -1); +} + void kick_defer_list_purge(struct softnet_data *sd, unsigned int cpu); #define XMIT_RECURSION_LIMIT 8 diff --git a/net/core/dev_api.c b/net/core/dev_api.c new file mode 100644 index 000000000000..90bafb0b1b8c --- /dev/null +++ b/net/core/dev_api.c @@ -0,0 +1,329 @@ +// SPDX-License-Identifier: GPL-2.0-or-later + +#include <linux/netdevice.h> +#include <net/netdev_lock.h> + +#include "dev.h" + +/** + * dev_change_name() - change name of a device + * @dev: device + * @newname: name (or format string) must be at least IFNAMSIZ + * + * Change name of a device, can pass format strings "eth%d". + * for wildcarding. + * + * Return: 0 on success, -errno on failure. + */ +int dev_change_name(struct net_device *dev, const char *newname) +{ + int ret; + + netdev_lock_ops(dev); + ret = netif_change_name(dev, newname); + netdev_unlock_ops(dev); + + return ret; +} + +/** + * dev_set_alias() - change ifalias of a device + * @dev: device + * @alias: name up to IFALIASZ + * @len: limit of bytes to copy from info + * + * Set ifalias for a device. + * + * Return: 0 on success, -errno on failure. + */ +int dev_set_alias(struct net_device *dev, const char *alias, size_t len) +{ + int ret; + + netdev_lock_ops(dev); + ret = netif_set_alias(dev, alias, len); + netdev_unlock_ops(dev); + + return ret; +} +EXPORT_SYMBOL(dev_set_alias); + +/** + * dev_change_flags() - change device settings + * @dev: device + * @flags: device state flags + * @extack: netlink extended ack + * + * Change settings on device based state flags. The flags are + * in the userspace exported format. + * + * Return: 0 on success, -errno on failure. + */ +int dev_change_flags(struct net_device *dev, unsigned int flags, + struct netlink_ext_ack *extack) +{ + int ret; + + netdev_lock_ops(dev); + ret = netif_change_flags(dev, flags, extack); + netdev_unlock_ops(dev); + + return ret; +} +EXPORT_SYMBOL(dev_change_flags); + +/** + * dev_set_group() - change group this device belongs to + * @dev: device + * @new_group: group this device should belong to + */ +void dev_set_group(struct net_device *dev, int new_group) +{ + netdev_lock_ops(dev); + netif_set_group(dev, new_group); + netdev_unlock_ops(dev); +} + +int dev_set_mac_address_user(struct net_device *dev, struct sockaddr *sa, + struct netlink_ext_ack *extack) +{ + int ret; + + down_write(&dev_addr_sem); + netdev_lock_ops(dev); + ret = netif_set_mac_address(dev, sa, extack); + netdev_unlock_ops(dev); + up_write(&dev_addr_sem); + + return ret; +} +EXPORT_SYMBOL(dev_set_mac_address_user); + +/** + * dev_change_net_namespace() - move device to different nethost namespace + * @dev: device + * @net: network namespace + * @pat: If not NULL name pattern to try if the current device name + * is already taken in the destination network namespace. + * + * This function shuts down a device interface and moves it + * to a new network namespace. On success 0 is returned, on + * a failure a netagive errno code is returned. + * + * Callers must hold the rtnl semaphore. + * + * Return: 0 on success, -errno on failure. + */ +int dev_change_net_namespace(struct net_device *dev, struct net *net, + const char *pat) +{ + return __dev_change_net_namespace(dev, net, pat, 0, NULL); +} +EXPORT_SYMBOL_GPL(dev_change_net_namespace); + +/** + * dev_change_carrier() - change device carrier + * @dev: device + * @new_carrier: new value + * + * Change device carrier + * + * Return: 0 on success, -errno on failure. + */ +int dev_change_carrier(struct net_device *dev, bool new_carrier) +{ + int ret; + + netdev_lock_ops(dev); + ret = netif_change_carrier(dev, new_carrier); + netdev_unlock_ops(dev); + + return ret; +} + +/** + * dev_change_tx_queue_len() - change TX queue length of a netdevice + * @dev: device + * @new_len: new tx queue length + * + * Return: 0 on success, -errno on failure. + */ +int dev_change_tx_queue_len(struct net_device *dev, unsigned long new_len) +{ + int ret; + + netdev_lock_ops(dev); + ret = netif_change_tx_queue_len(dev, new_len); + netdev_unlock_ops(dev); + + return ret; +} + +/** + * dev_change_proto_down() - set carrier according to proto_down + * @dev: device + * @proto_down: new value + * + * Return: 0 on success, -errno on failure. + */ +int dev_change_proto_down(struct net_device *dev, bool proto_down) +{ + int ret; + + netdev_lock_ops(dev); + ret = netif_change_proto_down(dev, proto_down); + netdev_unlock_ops(dev); + + return ret; +} + +/** + * dev_open() - prepare an interface for use + * @dev: device to open + * @extack: netlink extended ack + * + * Takes a device from down to up state. The device's private open + * function is invoked and then the multicast lists are loaded. Finally + * the device is moved into the up state and a %NETDEV_UP message is + * sent to the netdev notifier chain. + * + * Calling this function on an active interface is a nop. On a failure + * a negative errno code is returned. + * + * Return: 0 on success, -errno on failure. + */ +int dev_open(struct net_device *dev, struct netlink_ext_ack *extack) +{ + int ret; + + netdev_lock_ops(dev); + ret = netif_open(dev, extack); + netdev_unlock_ops(dev); + + return ret; +} +EXPORT_SYMBOL(dev_open); + +/** + * dev_close() - shutdown an interface + * @dev: device to shutdown + * + * This function moves an active device into down state. A + * %NETDEV_GOING_DOWN is sent to the netdev notifier chain. The device + * is then deactivated and finally a %NETDEV_DOWN is sent to the notifier + * chain. + */ +void dev_close(struct net_device *dev) +{ + netdev_lock_ops(dev); + netif_close(dev); + netdev_unlock_ops(dev); +} +EXPORT_SYMBOL(dev_close); + +int dev_eth_ioctl(struct net_device *dev, + struct ifreq *ifr, unsigned int cmd) +{ + const struct net_device_ops *ops = dev->netdev_ops; + int ret = -ENODEV; + + if (!ops->ndo_eth_ioctl) + return -EOPNOTSUPP; + + netdev_lock_ops(dev); + if (netif_device_present(dev)) + ret = ops->ndo_eth_ioctl(dev, ifr, cmd); + netdev_unlock_ops(dev); + + return ret; +} +EXPORT_SYMBOL(dev_eth_ioctl); + +int dev_set_mtu(struct net_device *dev, int new_mtu) +{ + int ret; + + netdev_lock_ops(dev); + ret = netif_set_mtu(dev, new_mtu); + netdev_unlock_ops(dev); + + return ret; +} +EXPORT_SYMBOL(dev_set_mtu); + +/** + * dev_disable_lro() - disable Large Receive Offload on a device + * @dev: device + * + * Disable Large Receive Offload (LRO) on a net device. Must be + * called under RTNL. This is needed if received packets may be + * forwarded to another interface. + */ +void dev_disable_lro(struct net_device *dev) +{ + netdev_lock_ops(dev); + netif_disable_lro(dev); + netdev_unlock_ops(dev); +} +EXPORT_SYMBOL(dev_disable_lro); + +/** + * dev_set_allmulti() - update allmulti count on a device + * @dev: device + * @inc: modifier + * + * Add or remove reception of all multicast frames to a device. While the + * count in the device remains above zero the interface remains listening + * to all interfaces. Once it hits zero the device reverts back to normal + * filtering operation. A negative @inc value is used to drop the counter + * when releasing a resource needing all multicasts. + * + * Return: 0 on success, -errno on failure. + */ + +int dev_set_allmulti(struct net_device *dev, int inc) +{ + int ret; + + netdev_lock_ops(dev); + ret = netif_set_allmulti(dev, inc, true); + netdev_unlock_ops(dev); + + return ret; +} +EXPORT_SYMBOL(dev_set_allmulti); + +/** + * dev_set_mac_address() - change Media Access Control Address + * @dev: device + * @sa: new address + * @extack: netlink extended ack + * + * Change the hardware (MAC) address of the device + * + * Return: 0 on success, -errno on failure. + */ +int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa, + struct netlink_ext_ack *extack) +{ + int ret; + + netdev_lock_ops(dev); + ret = netif_set_mac_address(dev, sa, extack); + netdev_unlock_ops(dev); + + return ret; +} +EXPORT_SYMBOL(dev_set_mac_address); + +int dev_xdp_propagate(struct net_device *dev, struct netdev_bpf *bpf) +{ + int ret; + + netdev_lock_ops(dev); + ret = netif_xdp_propagate(dev, bpf); + netdev_unlock_ops(dev); + + return ret; +} +EXPORT_SYMBOL_GPL(dev_xdp_propagate); diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c index 4c2098ac9d72..fff13a8b48f1 100644 --- a/net/core/dev_ioctl.c +++ b/net/core/dev_ioctl.c @@ -10,6 +10,7 @@ #include <linux/wireless.h> #include <linux/if_bridge.h> #include <net/dsa_stubs.h> +#include <net/netdev_lock.h> #include <net/wext.h> #include "dev.h" @@ -110,7 +111,7 @@ static int dev_getifmap(struct net_device *dev, struct ifreq *ifr) return 0; } -static int dev_setifmap(struct net_device *dev, struct ifreq *ifr) +static int netif_setifmap(struct net_device *dev, struct ifreq *ifr) { struct compat_ifmap *cifmap = (struct compat_ifmap *)&ifr->ifr_map; @@ -240,20 +241,6 @@ int net_hwtstamp_validate(const struct kernel_hwtstamp_config *cfg) return 0; } -static int dev_eth_ioctl(struct net_device *dev, - struct ifreq *ifr, unsigned int cmd) -{ - const struct net_device_ops *ops = dev->netdev_ops; - - if (!ops->ndo_eth_ioctl) - return -EOPNOTSUPP; - - if (!netif_device_present(dev)) - return -ENODEV; - - return ops->ndo_eth_ioctl(dev, ifr, cmd); -} - /** * dev_get_hwtstamp_phylib() - Get hardware timestamping settings of NIC * or of attached phylib PHY @@ -305,7 +292,9 @@ static int dev_get_hwtstamp(struct net_device *dev, struct ifreq *ifr) return -ENODEV; kernel_cfg.ifr = ifr; + netdev_lock_ops(dev); err = dev_get_hwtstamp_phylib(dev, &kernel_cfg); + netdev_unlock_ops(dev); if (err) return err; @@ -429,7 +418,9 @@ static int dev_set_hwtstamp(struct net_device *dev, struct ifreq *ifr) if (!netif_device_present(dev)) return -ENODEV; + netdev_lock_ops(dev); err = dev_set_hwtstamp_phylib(dev, &kernel_cfg, &extack); + netdev_unlock_ops(dev); if (err) return err; @@ -504,10 +495,14 @@ static int dev_siocbond(struct net_device *dev, const struct net_device_ops *ops = dev->netdev_ops; if (ops->ndo_siocbond) { + int ret = -ENODEV; + + netdev_lock_ops(dev); if (netif_device_present(dev)) - return ops->ndo_siocbond(dev, ifr, cmd); - else - return -ENODEV; + ret = ops->ndo_siocbond(dev, ifr, cmd); + netdev_unlock_ops(dev); + + return ret; } return -EOPNOTSUPP; @@ -519,10 +514,14 @@ static int dev_siocdevprivate(struct net_device *dev, struct ifreq *ifr, const struct net_device_ops *ops = dev->netdev_ops; if (ops->ndo_siocdevprivate) { + int ret = -ENODEV; + + netdev_lock_ops(dev); if (netif_device_present(dev)) - return ops->ndo_siocdevprivate(dev, ifr, data, cmd); - else - return -ENODEV; + ret = ops->ndo_siocdevprivate(dev, ifr, data, cmd); + netdev_unlock_ops(dev); + + return ret; } return -EOPNOTSUPP; @@ -533,10 +532,14 @@ static int dev_siocwandev(struct net_device *dev, struct if_settings *ifs) const struct net_device_ops *ops = dev->netdev_ops; if (ops->ndo_siocwandev) { + int ret = -ENODEV; + + netdev_lock_ops(dev); if (netif_device_present(dev)) - return ops->ndo_siocwandev(dev, ifs); - else - return -ENODEV; + ret = ops->ndo_siocwandev(dev, ifs); + netdev_unlock_ops(dev); + + return ret; } return -EOPNOTSUPP; @@ -551,7 +554,6 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, void __user *data, int err; struct net_device *dev = __dev_get_by_name(net, ifr->ifr_name); const struct net_device_ops *ops; - netdevice_tracker dev_tracker; if (!dev) return -ENODEV; @@ -580,11 +582,16 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, void __user *data, memcpy(dev->broadcast, ifr->ifr_hwaddr.sa_data, min(sizeof(ifr->ifr_hwaddr.sa_data_min), (size_t)dev->addr_len)); + netdev_lock_ops(dev); call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); + netdev_unlock_ops(dev); return 0; case SIOCSIFMAP: - return dev_setifmap(dev, ifr); + netdev_lock_ops(dev); + err = netif_setifmap(dev, ifr); + netdev_unlock_ops(dev); + return err; case SIOCADDMULTI: if (!ops->ndo_set_rx_mode || @@ -592,7 +599,10 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, void __user *data, return -EINVAL; if (!netif_device_present(dev)) return -ENODEV; - return dev_mc_add_global(dev, ifr->ifr_hwaddr.sa_data); + netdev_lock_ops(dev); + err = dev_mc_add_global(dev, ifr->ifr_hwaddr.sa_data); + netdev_unlock_ops(dev); + return err; case SIOCDELMULTI: if (!ops->ndo_set_rx_mode || @@ -600,7 +610,10 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, void __user *data, return -EINVAL; if (!netif_device_present(dev)) return -ENODEV; - return dev_mc_del_global(dev, ifr->ifr_hwaddr.sa_data); + netdev_lock_ops(dev); + err = dev_mc_del_global(dev, ifr->ifr_hwaddr.sa_data); + netdev_unlock_ops(dev); + return err; case SIOCSIFTXQLEN: if (ifr->ifr_qlen < 0) @@ -614,22 +627,6 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, void __user *data, case SIOCWANDEV: return dev_siocwandev(dev, &ifr->ifr_settings); - case SIOCBRADDIF: - case SIOCBRDELIF: - if (!netif_device_present(dev)) - return -ENODEV; - if (!netif_is_bridge_master(dev)) - return -EOPNOTSUPP; - - netdev_hold(dev, &dev_tracker, GFP_KERNEL); - rtnl_net_unlock(net); - - err = br_ioctl_call(net, netdev_priv(dev), cmd, ifr, NULL); - - netdev_put(dev, &dev_tracker); - rtnl_net_lock(net); - return err; - case SIOCDEVPRIVATE ... SIOCDEVPRIVATE + 15: return dev_siocdevprivate(dev, ifr, data, cmd); @@ -812,8 +809,6 @@ int dev_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr, case SIOCBONDRELEASE: case SIOCBONDSETHWADDR: case SIOCBONDCHANGEACTIVE: - case SIOCBRADDIF: - case SIOCBRDELIF: case SIOCSHWTSTAMP: if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; diff --git a/net/core/devmem.c b/net/core/devmem.c index 3bba3f018df0..6e27a47d0493 100644 --- a/net/core/devmem.c +++ b/net/core/devmem.c @@ -8,7 +8,6 @@ */ #include <linux/dma-buf.h> -#include <linux/ethtool_netlink.h> #include <linux/genalloc.h> #include <linux/mm.h> #include <linux/netdevice.h> @@ -16,6 +15,7 @@ #include <net/netdev_queues.h> #include <net/netdev_rx_queue.h> #include <net/page_pool/helpers.h> +#include <net/page_pool/memory_provider.h> #include <trace/events/page_pool.h> #include "devmem.h" @@ -24,23 +24,30 @@ /* Device memory support */ -/* Protected by rtnl_lock() */ static DEFINE_XARRAY_FLAGS(net_devmem_dmabuf_bindings, XA_FLAGS_ALLOC1); +static const struct memory_provider_ops dmabuf_devmem_ops; + +bool net_is_devmem_iov(struct net_iov *niov) +{ + return niov->pp->mp_ops == &dmabuf_devmem_ops; +} + static void net_devmem_dmabuf_free_chunk_owner(struct gen_pool *genpool, struct gen_pool_chunk *chunk, void *not_used) { struct dmabuf_genpool_chunk_owner *owner = chunk->owner; - kvfree(owner->niovs); + kvfree(owner->area.niovs); kfree(owner); } static dma_addr_t net_devmem_get_dma_addr(const struct net_iov *niov) { - struct dmabuf_genpool_chunk_owner *owner = net_iov_owner(niov); + struct dmabuf_genpool_chunk_owner *owner; + owner = net_devmem_iov_to_chunk_owner(niov); return owner->base_dma_addr + ((dma_addr_t)net_iov_idx(niov) << PAGE_SHIFT); } @@ -83,7 +90,7 @@ net_devmem_alloc_dmabuf(struct net_devmem_dmabuf_binding *binding) offset = dma_addr - owner->base_dma_addr; index = offset / PAGE_SIZE; - niov = &owner->niovs[index]; + niov = &owner->area.niovs[index]; niov->pp_magic = 0; niov->pp = NULL; @@ -94,7 +101,7 @@ net_devmem_alloc_dmabuf(struct net_devmem_dmabuf_binding *binding) void net_devmem_free_dmabuf(struct net_iov *niov) { - struct net_devmem_dmabuf_binding *binding = net_iov_binding(niov); + struct net_devmem_dmabuf_binding *binding = net_devmem_iov_binding(niov); unsigned long dma_addr = net_devmem_get_dma_addr(niov); if (WARN_ON(!gen_pool_has_addr(binding->chunk_pool, dma_addr, @@ -114,13 +121,14 @@ void net_devmem_unbind_dmabuf(struct net_devmem_dmabuf_binding *binding) list_del(&binding->list); xa_for_each(&binding->bound_rxqs, xa_idx, rxq) { - WARN_ON(rxq->mp_params.mp_priv != binding); - - rxq->mp_params.mp_priv = NULL; + const struct pp_memory_provider_params mp_params = { + .mp_priv = binding, + .mp_ops = &dmabuf_devmem_ops, + }; rxq_idx = get_netdev_rx_queue_index(rxq); - WARN_ON(netdev_rx_queue_restart(binding->dev, rxq_idx)); + __net_mp_close_rxq(binding->dev, rxq_idx, &mp_params); } xa_erase(&net_devmem_dmabuf_bindings, binding->id); @@ -132,55 +140,28 @@ int net_devmem_bind_dmabuf_to_queue(struct net_device *dev, u32 rxq_idx, struct net_devmem_dmabuf_binding *binding, struct netlink_ext_ack *extack) { + struct pp_memory_provider_params mp_params = { + .mp_priv = binding, + .mp_ops = &dmabuf_devmem_ops, + }; struct netdev_rx_queue *rxq; u32 xa_idx; int err; - if (rxq_idx >= dev->real_num_rx_queues) { - NL_SET_ERR_MSG(extack, "rx queue index out of range"); - return -ERANGE; - } - - if (dev->cfg->hds_config != ETHTOOL_TCP_DATA_SPLIT_ENABLED) { - NL_SET_ERR_MSG(extack, "tcp-data-split is disabled"); - return -EINVAL; - } - - if (dev->cfg->hds_thresh) { - NL_SET_ERR_MSG(extack, "hds-thresh is not zero"); - return -EINVAL; - } + err = __net_mp_open_rxq(dev, rxq_idx, &mp_params, extack); + if (err) + return err; rxq = __netif_get_rx_queue(dev, rxq_idx); - if (rxq->mp_params.mp_priv) { - NL_SET_ERR_MSG(extack, "designated queue already memory provider bound"); - return -EEXIST; - } - -#ifdef CONFIG_XDP_SOCKETS - if (rxq->pool) { - NL_SET_ERR_MSG(extack, "designated queue already in use by AF_XDP"); - return -EBUSY; - } -#endif - err = xa_alloc(&binding->bound_rxqs, &xa_idx, rxq, xa_limit_32b, GFP_KERNEL); if (err) - return err; - - rxq->mp_params.mp_priv = binding; - - err = netdev_rx_queue_restart(dev, rxq_idx); - if (err) - goto err_xa_erase; + goto err_close_rxq; return 0; -err_xa_erase: - rxq->mp_params.mp_priv = NULL; - xa_erase(&binding->bound_rxqs, xa_idx); - +err_close_rxq: + __net_mp_close_rxq(dev, rxq_idx, &mp_params); return err; } @@ -261,9 +242,9 @@ net_devmem_bind_dmabuf(struct net_device *dev, unsigned int dmabuf_fd, goto err_free_chunks; } - owner->base_virtual = virtual; + owner->area.base_virtual = virtual; owner->base_dma_addr = dma_addr; - owner->num_niovs = len / PAGE_SIZE; + owner->area.num_niovs = len / PAGE_SIZE; owner->binding = binding; err = gen_pool_add_owner(binding->chunk_pool, dma_addr, @@ -275,17 +256,17 @@ net_devmem_bind_dmabuf(struct net_device *dev, unsigned int dmabuf_fd, goto err_free_chunks; } - owner->niovs = kvmalloc_array(owner->num_niovs, - sizeof(*owner->niovs), - GFP_KERNEL); - if (!owner->niovs) { + owner->area.niovs = kvmalloc_array(owner->area.num_niovs, + sizeof(*owner->area.niovs), + GFP_KERNEL); + if (!owner->area.niovs) { err = -ENOMEM; goto err_free_chunks; } - for (i = 0; i < owner->num_niovs; i++) { - niov = &owner->niovs[i]; - niov->owner = owner; + for (i = 0; i < owner->area.num_niovs; i++) { + niov = &owner->area.niovs[i]; + niov->owner = &owner->area; page_pool_set_dma_addr_netmem(net_iov_to_netmem(niov), net_devmem_get_dma_addr(niov)); } @@ -313,26 +294,6 @@ err_put_dmabuf: return ERR_PTR(err); } -void dev_dmabuf_uninstall(struct net_device *dev) -{ - struct net_devmem_dmabuf_binding *binding; - struct netdev_rx_queue *rxq; - unsigned long xa_idx; - unsigned int i; - - for (i = 0; i < dev->real_num_rx_queues; i++) { - binding = dev->_rx[i].mp_params.mp_priv; - if (!binding) - continue; - - xa_for_each(&binding->bound_rxqs, xa_idx, rxq) - if (rxq == &dev->_rx[i]) { - xa_erase(&binding->bound_rxqs, xa_idx); - break; - } - } -} - /*** "Dmabuf devmem memory provider" ***/ int mp_dmabuf_devmem_init(struct page_pool *pool) @@ -398,3 +359,36 @@ bool mp_dmabuf_devmem_release_page(struct page_pool *pool, netmem_ref netmem) /* We don't want the page pool put_page()ing our net_iovs. */ return false; } + +static int mp_dmabuf_devmem_nl_fill(void *mp_priv, struct sk_buff *rsp, + struct netdev_rx_queue *rxq) +{ + const struct net_devmem_dmabuf_binding *binding = mp_priv; + int type = rxq ? NETDEV_A_QUEUE_DMABUF : NETDEV_A_PAGE_POOL_DMABUF; + + return nla_put_u32(rsp, type, binding->id); +} + +static void mp_dmabuf_devmem_uninstall(void *mp_priv, + struct netdev_rx_queue *rxq) +{ + struct net_devmem_dmabuf_binding *binding = mp_priv; + struct netdev_rx_queue *bound_rxq; + unsigned long xa_idx; + + xa_for_each(&binding->bound_rxqs, xa_idx, bound_rxq) { + if (bound_rxq == rxq) { + xa_erase(&binding->bound_rxqs, xa_idx); + break; + } + } +} + +static const struct memory_provider_ops dmabuf_devmem_ops = { + .init = mp_dmabuf_devmem_init, + .destroy = mp_dmabuf_devmem_destroy, + .alloc_netmems = mp_dmabuf_devmem_alloc_netmems, + .release_netmem = mp_dmabuf_devmem_release_page, + .nl_fill = mp_dmabuf_devmem_nl_fill, + .uninstall = mp_dmabuf_devmem_uninstall, +}; diff --git a/net/core/devmem.h b/net/core/devmem.h index 76099ef9c482..7fc158d52729 100644 --- a/net/core/devmem.h +++ b/net/core/devmem.h @@ -10,6 +10,8 @@ #ifndef _NET_DEVMEM_H #define _NET_DEVMEM_H +#include <net/netmem.h> + struct netlink_ext_ack; struct net_devmem_dmabuf_binding { @@ -51,17 +53,11 @@ struct net_devmem_dmabuf_binding { * allocations from this chunk. */ struct dmabuf_genpool_chunk_owner { - /* Offset into the dma-buf where this chunk starts. */ - unsigned long base_virtual; + struct net_iov_area area; + struct net_devmem_dmabuf_binding *binding; /* dma_addr of the start of the chunk. */ dma_addr_t base_dma_addr; - - /* Array of net_iovs for this chunk. */ - struct net_iov *niovs; - size_t num_niovs; - - struct net_devmem_dmabuf_binding *binding; }; void __net_devmem_dmabuf_binding_free(struct net_devmem_dmabuf_binding *binding); @@ -72,38 +68,34 @@ void net_devmem_unbind_dmabuf(struct net_devmem_dmabuf_binding *binding); int net_devmem_bind_dmabuf_to_queue(struct net_device *dev, u32 rxq_idx, struct net_devmem_dmabuf_binding *binding, struct netlink_ext_ack *extack); -void dev_dmabuf_uninstall(struct net_device *dev); static inline struct dmabuf_genpool_chunk_owner * -net_iov_owner(const struct net_iov *niov) +net_devmem_iov_to_chunk_owner(const struct net_iov *niov) { - return niov->owner; + struct net_iov_area *owner = net_iov_owner(niov); + + return container_of(owner, struct dmabuf_genpool_chunk_owner, area); } -static inline unsigned int net_iov_idx(const struct net_iov *niov) +static inline struct net_devmem_dmabuf_binding * +net_devmem_iov_binding(const struct net_iov *niov) { - return niov - net_iov_owner(niov)->niovs; + return net_devmem_iov_to_chunk_owner(niov)->binding; } -static inline struct net_devmem_dmabuf_binding * -net_iov_binding(const struct net_iov *niov) +static inline u32 net_devmem_iov_binding_id(const struct net_iov *niov) { - return net_iov_owner(niov)->binding; + return net_devmem_iov_binding(niov)->id; } static inline unsigned long net_iov_virtual_addr(const struct net_iov *niov) { - struct dmabuf_genpool_chunk_owner *owner = net_iov_owner(niov); + struct net_iov_area *owner = net_iov_owner(niov); return owner->base_virtual + ((unsigned long)net_iov_idx(niov) << PAGE_SHIFT); } -static inline u32 net_iov_binding_id(const struct net_iov *niov) -{ - return net_iov_owner(niov)->binding->id; -} - static inline void net_devmem_dmabuf_binding_get(struct net_devmem_dmabuf_binding *binding) { @@ -123,6 +115,8 @@ struct net_iov * net_devmem_alloc_dmabuf(struct net_devmem_dmabuf_binding *binding); void net_devmem_free_dmabuf(struct net_iov *ppiov); +bool net_is_devmem_iov(struct net_iov *niov); + #else struct net_devmem_dmabuf_binding; @@ -152,10 +146,6 @@ net_devmem_bind_dmabuf_to_queue(struct net_device *dev, u32 rxq_idx, return -EOPNOTSUPP; } -static inline void dev_dmabuf_uninstall(struct net_device *dev) -{ -} - static inline struct net_iov * net_devmem_alloc_dmabuf(struct net_devmem_dmabuf_binding *binding) { @@ -171,10 +161,15 @@ static inline unsigned long net_iov_virtual_addr(const struct net_iov *niov) return 0; } -static inline u32 net_iov_binding_id(const struct net_iov *niov) +static inline u32 net_devmem_iov_binding_id(const struct net_iov *niov) { return 0; } + +static inline bool net_is_devmem_iov(struct net_iov *niov) +{ + return false; +} #endif #endif /* _NET_DEVMEM_H */ diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c index 6efd4cccc9dd..8a7ce640f74d 100644 --- a/net/core/drop_monitor.c +++ b/net/core/drop_monitor.c @@ -1088,7 +1088,7 @@ err_module_put: struct per_cpu_dm_data *hw_data = &per_cpu(dm_hw_cpu_data, cpu); struct sk_buff *skb; - del_timer_sync(&hw_data->send_timer); + timer_delete_sync(&hw_data->send_timer); cancel_work_sync(&hw_data->dm_alert_work); while ((skb = __skb_dequeue(&hw_data->drop_queue))) { struct devlink_trap_metadata *hw_metadata; @@ -1122,7 +1122,7 @@ static void net_dm_hw_monitor_stop(struct netlink_ext_ack *extack) struct per_cpu_dm_data *hw_data = &per_cpu(dm_hw_cpu_data, cpu); struct sk_buff *skb; - del_timer_sync(&hw_data->send_timer); + timer_delete_sync(&hw_data->send_timer); cancel_work_sync(&hw_data->dm_alert_work); while ((skb = __skb_dequeue(&hw_data->drop_queue))) { struct devlink_trap_metadata *hw_metadata; @@ -1183,7 +1183,7 @@ err_module_put: struct per_cpu_dm_data *data = &per_cpu(dm_cpu_data, cpu); struct sk_buff *skb; - del_timer_sync(&data->send_timer); + timer_delete_sync(&data->send_timer); cancel_work_sync(&data->dm_alert_work); while ((skb = __skb_dequeue(&data->drop_queue))) consume_skb(skb); @@ -1211,7 +1211,7 @@ static void net_dm_trace_off_set(void) struct per_cpu_dm_data *data = &per_cpu(dm_cpu_data, cpu); struct sk_buff *skb; - del_timer_sync(&data->send_timer); + timer_delete_sync(&data->send_timer); cancel_work_sync(&data->dm_alert_work); while ((skb = __skb_dequeue(&data->drop_queue))) consume_skb(skb); @@ -1734,30 +1734,30 @@ static int __init init_net_drop_monitor(void) return -ENOSPC; } - rc = genl_register_family(&net_drop_monitor_family); - if (rc) { - pr_err("Could not create drop monitor netlink family\n"); - return rc; + for_each_possible_cpu(cpu) { + net_dm_cpu_data_init(cpu); + net_dm_hw_cpu_data_init(cpu); } - WARN_ON(net_drop_monitor_family.mcgrp_offset != NET_DM_GRP_ALERT); rc = register_netdevice_notifier(&dropmon_net_notifier); if (rc < 0) { pr_crit("Failed to register netdevice notifier\n"); + return rc; + } + + rc = genl_register_family(&net_drop_monitor_family); + if (rc) { + pr_err("Could not create drop monitor netlink family\n"); goto out_unreg; } + WARN_ON(net_drop_monitor_family.mcgrp_offset != NET_DM_GRP_ALERT); rc = 0; - for_each_possible_cpu(cpu) { - net_dm_cpu_data_init(cpu); - net_dm_hw_cpu_data_init(cpu); - } - goto out; out_unreg: - genl_unregister_family(&net_drop_monitor_family); + WARN_ON(unregister_netdevice_notifier(&dropmon_net_notifier)); out: return rc; } @@ -1766,19 +1766,18 @@ static void exit_net_drop_monitor(void) { int cpu; - BUG_ON(unregister_netdevice_notifier(&dropmon_net_notifier)); - /* * Because of the module_get/put we do in the trace state change path * we are guaranteed not to have any current users when we get here */ + BUG_ON(genl_unregister_family(&net_drop_monitor_family)); + + BUG_ON(unregister_netdevice_notifier(&dropmon_net_notifier)); for_each_possible_cpu(cpu) { net_dm_hw_cpu_data_fini(cpu); net_dm_cpu_data_fini(cpu); } - - BUG_ON(genl_unregister_family(&net_drop_monitor_family)); } module_init(init_net_drop_monitor); diff --git a/net/core/dst.c b/net/core/dst.c index 9552a90d4772..795ca07e28a4 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -165,6 +165,14 @@ static void dst_count_dec(struct dst_entry *dst) void dst_release(struct dst_entry *dst) { if (dst && rcuref_put(&dst->__rcuref)) { +#ifdef CONFIG_DST_CACHE + if (dst->flags & DST_METADATA) { + struct metadata_dst *md_dst = (struct metadata_dst *)dst; + + if (md_dst->type == METADATA_IP_TUNNEL) + dst_cache_reset_now(&md_dst->u.tun_info.dst_cache); + } +#endif dst_count_dec(dst); call_rcu_hurry(&dst->rcu_head, dst_destroy_rcu); } @@ -286,7 +294,8 @@ struct metadata_dst *metadata_dst_alloc(u8 optslen, enum metadata_type type, { struct metadata_dst *md_dst; - md_dst = kmalloc(sizeof(*md_dst) + optslen, flags); + md_dst = kmalloc(struct_size(md_dst, u.tun_info.options, optslen), + flags); if (!md_dst) return NULL; @@ -314,7 +323,8 @@ metadata_dst_alloc_percpu(u8 optslen, enum metadata_type type, gfp_t flags) int cpu; struct metadata_dst __percpu *md_dst; - md_dst = __alloc_percpu_gfp(sizeof(struct metadata_dst) + optslen, + md_dst = __alloc_percpu_gfp(struct_size(md_dst, u.tun_info.options, + optslen), __alignof__(struct metadata_dst), flags); if (!md_dst) return NULL; diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index e684ba3ebb38..4bc64d912a1c 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -37,8 +37,8 @@ static const struct fib_kuid_range fib_kuid_range_unset = { bool fib_rule_matchall(const struct fib_rule *rule) { - if (rule->iifindex || rule->oifindex || rule->mark || rule->tun_id || - rule->flags) + if (READ_ONCE(rule->iifindex) || READ_ONCE(rule->oifindex) || + rule->mark || rule->tun_id || rule->flags) return false; if (rule->suppress_ifgroup != -1 || rule->suppress_prefixlen != -1) return false; @@ -261,12 +261,14 @@ static int fib_rule_match(struct fib_rule *rule, struct fib_rules_ops *ops, struct flowi *fl, int flags, struct fib_lookup_arg *arg) { - int ret = 0; + int iifindex, oifindex, ret = 0; - if (rule->iifindex && (rule->iifindex != fl->flowi_iif)) + iifindex = READ_ONCE(rule->iifindex); + if (iifindex && (iifindex != fl->flowi_iif)) goto out; - if (rule->oifindex && (rule->oifindex != fl->flowi_oif)) + oifindex = READ_ONCE(rule->oifindex); + if (oifindex && (oifindex != fl->flowi_oif)) goto out; if ((rule->mark ^ fl->flowi_mark) & rule->mark_mask) @@ -371,7 +373,8 @@ static int call_fib_rule_notifiers(struct net *net, .rule = rule, }; - ASSERT_RTNL(); + ASSERT_RTNL_NET(net); + /* Paired with READ_ONCE() in fib_rules_seq() */ WRITE_ONCE(ops->fib_rules_seq, ops->fib_rules_seq + 1); return call_fib_notifiers(net, event_type, &info.info); @@ -459,9 +462,6 @@ static struct fib_rule *rule_find(struct fib_rules_ops *ops, if (rule->tun_id && r->tun_id != rule->tun_id) continue; - if (r->fr_net != rule->fr_net) - continue; - if (rule->l3mdev && r->l3mdev != rule->l3mdev) continue; @@ -481,11 +481,17 @@ static struct fib_rule *rule_find(struct fib_rules_ops *ops, &rule->sport_range)) continue; + if (rule->sport_mask && r->sport_mask != rule->sport_mask) + continue; + if (fib_rule_port_range_set(&rule->dport_range) && !fib_rule_port_range_compare(&r->dport_range, &rule->dport_range)) continue; + if (rule->dport_mask && r->dport_mask != rule->dport_mask) + continue; + if (!ops->compare(r, frh, tb)) continue; return r; @@ -515,14 +521,40 @@ static int fib_nl2rule_l3mdev(struct nlattr *nla, struct fib_rule *nlrule, } #endif -static int fib_nl2rule(struct sk_buff *skb, struct nlmsghdr *nlh, +static int fib_nl2rule_port_mask(const struct nlattr *mask_attr, + const struct fib_rule_port_range *range, + u16 *port_mask, + struct netlink_ext_ack *extack) +{ + if (!fib_rule_port_range_valid(range)) { + NL_SET_ERR_MSG_ATTR(extack, mask_attr, + "Cannot specify port mask without port value"); + return -EINVAL; + } + + if (fib_rule_port_is_range(range)) { + NL_SET_ERR_MSG_ATTR(extack, mask_attr, + "Cannot specify port mask for port range"); + return -EINVAL; + } + + if (range->start & ~nla_get_u16(mask_attr)) { + NL_SET_ERR_MSG_ATTR(extack, mask_attr, "Invalid port mask"); + return -EINVAL; + } + + *port_mask = nla_get_u16(mask_attr); + + return 0; +} + +static int fib_nl2rule(struct net *net, struct nlmsghdr *nlh, struct netlink_ext_ack *extack, struct fib_rules_ops *ops, struct nlattr *tb[], struct fib_rule **rule, bool *user_priority) { - struct net *net = sock_net(skb->sk); struct fib_rule_hdr *frh = nlmsg_data(nlh); struct fib_rule *nlrule = NULL; int err = -EINVAL; @@ -554,30 +586,18 @@ static int fib_nl2rule(struct sk_buff *skb, struct nlmsghdr *nlh, if (tb[FRA_PRIORITY]) { nlrule->pref = nla_get_u32(tb[FRA_PRIORITY]); *user_priority = true; - } else { - nlrule->pref = fib_default_rule_pref(ops); } nlrule->proto = nla_get_u8_default(tb[FRA_PROTOCOL], RTPROT_UNSPEC); if (tb[FRA_IIFNAME]) { - struct net_device *dev; - nlrule->iifindex = -1; nla_strscpy(nlrule->iifname, tb[FRA_IIFNAME], IFNAMSIZ); - dev = __dev_get_by_name(net, nlrule->iifname); - if (dev) - nlrule->iifindex = dev->ifindex; } if (tb[FRA_OIFNAME]) { - struct net_device *dev; - nlrule->oifindex = -1; nla_strscpy(nlrule->oifname, tb[FRA_OIFNAME], IFNAMSIZ); - dev = __dev_get_by_name(net, nlrule->oifname); - if (dev) - nlrule->oifindex = dev->ifindex; } if (tb[FRA_FWMARK]) { @@ -619,11 +639,6 @@ static int fib_nl2rule(struct sk_buff *skb, struct nlmsghdr *nlh, } nlrule->target = nla_get_u32(tb[FRA_GOTO]); - /* Backward jumps are prohibited to avoid endless loops */ - if (nlrule->target <= nlrule->pref) { - NL_SET_ERR_MSG(extack, "Backward goto not supported"); - goto errout_free; - } } else if (nlrule->action == FR_ACT_GOTO) { NL_SET_ERR_MSG(extack, "Missing goto target for action goto"); goto errout_free; @@ -662,6 +677,16 @@ static int fib_nl2rule(struct sk_buff *skb, struct nlmsghdr *nlh, NL_SET_ERR_MSG(extack, "Invalid sport range"); goto errout_free; } + if (!fib_rule_port_is_range(&nlrule->sport_range)) + nlrule->sport_mask = U16_MAX; + } + + if (tb[FRA_SPORT_MASK]) { + err = fib_nl2rule_port_mask(tb[FRA_SPORT_MASK], + &nlrule->sport_range, + &nlrule->sport_mask, extack); + if (err) + goto errout_free; } if (tb[FRA_DPORT_RANGE]) { @@ -671,6 +696,16 @@ static int fib_nl2rule(struct sk_buff *skb, struct nlmsghdr *nlh, NL_SET_ERR_MSG(extack, "Invalid dport range"); goto errout_free; } + if (!fib_rule_port_is_range(&nlrule->dport_range)) + nlrule->dport_mask = U16_MAX; + } + + if (tb[FRA_DPORT_MASK]) { + err = fib_nl2rule_port_mask(tb[FRA_DPORT_MASK], + &nlrule->dport_range, + &nlrule->dport_mask, extack); + if (err) + goto errout_free; } *rule = nlrule; @@ -683,6 +718,39 @@ errout: return err; } +static int fib_nl2rule_rtnl(struct fib_rule *nlrule, + struct fib_rules_ops *ops, + struct nlattr *tb[], + struct netlink_ext_ack *extack) +{ + if (!tb[FRA_PRIORITY]) + nlrule->pref = fib_default_rule_pref(ops); + + /* Backward jumps are prohibited to avoid endless loops */ + if (tb[FRA_GOTO] && nlrule->target <= nlrule->pref) { + NL_SET_ERR_MSG(extack, "Backward goto not supported"); + return -EINVAL; + } + + if (tb[FRA_IIFNAME]) { + struct net_device *dev; + + dev = __dev_get_by_name(nlrule->fr_net, nlrule->iifname); + if (dev) + nlrule->iifindex = dev->ifindex; + } + + if (tb[FRA_OIFNAME]) { + struct net_device *dev; + + dev = __dev_get_by_name(nlrule->fr_net, nlrule->oifname); + if (dev) + nlrule->oifindex = dev->ifindex; + } + + return 0; +} + static int rule_exists(struct fib_rules_ops *ops, struct fib_rule_hdr *frh, struct nlattr **tb, struct fib_rule *rule) { @@ -719,9 +787,6 @@ static int rule_exists(struct fib_rules_ops *ops, struct fib_rule_hdr *frh, if (r->tun_id != rule->tun_id) continue; - if (r->fr_net != rule->fr_net) - continue; - if (r->l3mdev != rule->l3mdev) continue; @@ -739,10 +804,16 @@ static int rule_exists(struct fib_rules_ops *ops, struct fib_rule_hdr *frh, &rule->sport_range)) continue; + if (r->sport_mask != rule->sport_mask) + continue; + if (!fib_rule_port_range_compare(&r->dport_range, &rule->dport_range)) continue; + if (r->dport_mask != rule->dport_mask) + continue; + if (!ops->compare(r, frh, tb)) continue; return 1; @@ -772,17 +843,19 @@ static const struct nla_policy fib_rule_policy[FRA_MAX + 1] = { [FRA_DSCP] = NLA_POLICY_MAX(NLA_U8, INET_DSCP_MASK >> 2), [FRA_FLOWLABEL] = { .type = NLA_BE32 }, [FRA_FLOWLABEL_MASK] = { .type = NLA_BE32 }, + [FRA_SPORT_MASK] = { .type = NLA_U16 }, + [FRA_DPORT_MASK] = { .type = NLA_U16 }, + [FRA_DSCP_MASK] = NLA_POLICY_MASK(NLA_U8, INET_DSCP_MASK >> 2), }; -int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh, - struct netlink_ext_ack *extack) +int fib_newrule(struct net *net, struct sk_buff *skb, struct nlmsghdr *nlh, + struct netlink_ext_ack *extack, bool rtnl_held) { - struct net *net = sock_net(skb->sk); + struct fib_rule *rule = NULL, *r, *last = NULL; struct fib_rule_hdr *frh = nlmsg_data(nlh); + int err = -EINVAL, unresolved = 0; struct fib_rules_ops *ops = NULL; - struct fib_rule *rule = NULL, *r, *last = NULL; struct nlattr *tb[FRA_MAX + 1]; - int err = -EINVAL, unresolved = 0; bool user_priority = false; if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*frh))) { @@ -804,10 +877,17 @@ int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh, goto errout; } - err = fib_nl2rule(skb, nlh, extack, ops, tb, &rule, &user_priority); + err = fib_nl2rule(net, nlh, extack, ops, tb, &rule, &user_priority); if (err) goto errout; + if (!rtnl_held) + rtnl_net_lock(net); + + err = fib_nl2rule_rtnl(rule, ops, tb, extack); + if (err) + goto errout_free; + if ((nlh->nlmsg_flags & NLM_F_EXCL) && rule_exists(ops, frh, tb, rule)) { err = -EEXIST; @@ -869,29 +949,42 @@ int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh, if (rule->tun_id) ip_tunnel_need_metadata(); + fib_rule_get(rule); + + if (!rtnl_held) + rtnl_net_unlock(net); + notify_rule_change(RTM_NEWRULE, rule, ops, nlh, NETLINK_CB(skb).portid); + fib_rule_put(rule); flush_route_cache(ops); rules_ops_put(ops); return 0; errout_free: + if (!rtnl_held) + rtnl_net_unlock(net); kfree(rule); errout: rules_ops_put(ops); return err; } -EXPORT_SYMBOL_GPL(fib_nl_newrule); +EXPORT_SYMBOL_GPL(fib_newrule); -int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh, - struct netlink_ext_ack *extack) +static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh, + struct netlink_ext_ack *extack) { - struct net *net = sock_net(skb->sk); + return fib_newrule(sock_net(skb->sk), skb, nlh, extack, false); +} + +int fib_delrule(struct net *net, struct sk_buff *skb, struct nlmsghdr *nlh, + struct netlink_ext_ack *extack, bool rtnl_held) +{ + struct fib_rule *rule = NULL, *nlrule = NULL; struct fib_rule_hdr *frh = nlmsg_data(nlh); struct fib_rules_ops *ops = NULL; - struct fib_rule *rule = NULL, *r, *nlrule = NULL; struct nlattr *tb[FRA_MAX+1]; - int err = -EINVAL; bool user_priority = false; + int err = -EINVAL; if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*frh))) { NL_SET_ERR_MSG(extack, "Invalid msg length"); @@ -912,25 +1005,32 @@ int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh, goto errout; } - err = fib_nl2rule(skb, nlh, extack, ops, tb, &nlrule, &user_priority); + err = fib_nl2rule(net, nlh, extack, ops, tb, &nlrule, &user_priority); if (err) goto errout; + if (!rtnl_held) + rtnl_net_lock(net); + + err = fib_nl2rule_rtnl(nlrule, ops, tb, extack); + if (err) + goto errout_free; + rule = rule_find(ops, frh, tb, nlrule, user_priority); if (!rule) { err = -ENOENT; - goto errout; + goto errout_free; } if (rule->flags & FIB_RULE_PERMANENT) { err = -EPERM; - goto errout; + goto errout_free; } if (ops->delete) { err = ops->delete(rule); if (err) - goto errout; + goto errout_free; } if (rule->tun_id) @@ -952,7 +1052,7 @@ int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh, * current if it is goto rule, have actually been added. */ if (ops->nr_goto_rules > 0) { - struct fib_rule *n; + struct fib_rule *n, *r; n = list_next_entry(rule, list); if (&n->list == &ops->rules_list || n->pref != rule->pref) @@ -966,22 +1066,33 @@ int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh, } } - call_fib_rule_notifiers(net, FIB_EVENT_RULE_DEL, rule, ops, - NULL); - notify_rule_change(RTM_DELRULE, rule, ops, nlh, - NETLINK_CB(skb).portid); + call_fib_rule_notifiers(net, FIB_EVENT_RULE_DEL, rule, ops, NULL); + + if (!rtnl_held) + rtnl_net_unlock(net); + + notify_rule_change(RTM_DELRULE, rule, ops, nlh, NETLINK_CB(skb).portid); fib_rule_put(rule); flush_route_cache(ops); rules_ops_put(ops); kfree(nlrule); return 0; -errout: +errout_free: + if (!rtnl_held) + rtnl_net_unlock(net); kfree(nlrule); +errout: rules_ops_put(ops); return err; } -EXPORT_SYMBOL_GPL(fib_nl_delrule); +EXPORT_SYMBOL_GPL(fib_delrule); + +static int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh, + struct netlink_ext_ack *extack) +{ + return fib_delrule(sock_net(skb->sk), skb, nlh, extack, false); +} static inline size_t fib_rule_nlmsg_size(struct fib_rules_ops *ops, struct fib_rule *rule) @@ -1000,7 +1111,9 @@ static inline size_t fib_rule_nlmsg_size(struct fib_rules_ops *ops, + nla_total_size(1) /* FRA_PROTOCOL */ + nla_total_size(1) /* FRA_IP_PROTO */ + nla_total_size(sizeof(struct fib_rule_port_range)) /* FRA_SPORT_RANGE */ - + nla_total_size(sizeof(struct fib_rule_port_range)); /* FRA_DPORT_RANGE */ + + nla_total_size(sizeof(struct fib_rule_port_range)) /* FRA_DPORT_RANGE */ + + nla_total_size(2) /* FRA_SPORT_MASK */ + + nla_total_size(2); /* FRA_DPORT_MASK */ if (ops->nlmsg_payload) payload += ops->nlmsg_payload(rule); @@ -1041,14 +1154,14 @@ static int fib_nl_fill_rule(struct sk_buff *skb, struct fib_rule *rule, if (rule->iifname[0]) { if (nla_put_string(skb, FRA_IIFNAME, rule->iifname)) goto nla_put_failure; - if (rule->iifindex == -1) + if (READ_ONCE(rule->iifindex) == -1) frh->flags |= FIB_RULE_IIF_DETACHED; } if (rule->oifname[0]) { if (nla_put_string(skb, FRA_OIFNAME, rule->oifname)) goto nla_put_failure; - if (rule->oifindex == -1) + if (READ_ONCE(rule->oifindex) == -1) frh->flags |= FIB_RULE_OIF_DETACHED; } @@ -1068,8 +1181,12 @@ static int fib_nl_fill_rule(struct sk_buff *skb, struct fib_rule *rule, nla_put_uid_range(skb, &rule->uid_range)) || (fib_rule_port_range_set(&rule->sport_range) && nla_put_port_range(skb, FRA_SPORT_RANGE, &rule->sport_range)) || + (rule->sport_mask && nla_put_u16(skb, FRA_SPORT_MASK, + rule->sport_mask)) || (fib_rule_port_range_set(&rule->dport_range) && nla_put_port_range(skb, FRA_DPORT_RANGE, &rule->dport_range)) || + (rule->dport_mask && nla_put_u16(skb, FRA_DPORT_MASK, + rule->dport_mask)) || (rule->ip_proto && nla_put_u8(skb, FRA_IP_PROTO, rule->ip_proto))) goto nla_put_failure; @@ -1220,10 +1337,10 @@ static void attach_rules(struct list_head *rules, struct net_device *dev) list_for_each_entry(rule, rules, list) { if (rule->iifindex == -1 && strcmp(dev->name, rule->iifname) == 0) - rule->iifindex = dev->ifindex; + WRITE_ONCE(rule->iifindex, dev->ifindex); if (rule->oifindex == -1 && strcmp(dev->name, rule->oifname) == 0) - rule->oifindex = dev->ifindex; + WRITE_ONCE(rule->oifindex, dev->ifindex); } } @@ -1233,9 +1350,9 @@ static void detach_rules(struct list_head *rules, struct net_device *dev) list_for_each_entry(rule, rules, list) { if (rule->iifindex == dev->ifindex) - rule->iifindex = -1; + WRITE_ONCE(rule->iifindex, -1); if (rule->oifindex == dev->ifindex) - rule->oifindex = -1; + WRITE_ONCE(rule->oifindex, -1); } } @@ -1293,8 +1410,10 @@ static struct pernet_operations fib_rules_net_ops = { }; static const struct rtnl_msg_handler fib_rules_rtnl_msg_handlers[] __initconst = { - {.msgtype = RTM_NEWRULE, .doit = fib_nl_newrule}, - {.msgtype = RTM_DELRULE, .doit = fib_nl_delrule}, + {.msgtype = RTM_NEWRULE, .doit = fib_nl_newrule, + .flags = RTNL_FLAG_DOIT_PERNET}, + {.msgtype = RTM_DELRULE, .doit = fib_nl_delrule, + .flags = RTNL_FLAG_DOIT_PERNET}, {.msgtype = RTM_GETRULE, .dumpit = fib_nl_dumprule, .flags = RTNL_FLAG_DUMP_UNLOCKED}, }; diff --git a/net/core/filter.c b/net/core/filter.c index 2ec162dd83c4..bc6828761a47 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -5222,6 +5222,25 @@ static const struct bpf_func_proto bpf_get_socket_uid_proto = { .arg1_type = ARG_PTR_TO_CTX, }; +static int sk_bpf_set_get_cb_flags(struct sock *sk, char *optval, bool getopt) +{ + u32 sk_bpf_cb_flags; + + if (getopt) { + *(u32 *)optval = sk->sk_bpf_cb_flags; + return 0; + } + + sk_bpf_cb_flags = *(u32 *)optval; + + if (sk_bpf_cb_flags & ~SK_BPF_CB_MASK) + return -EINVAL; + + sk->sk_bpf_cb_flags = sk_bpf_cb_flags; + + return 0; +} + static int sol_socket_sockopt(struct sock *sk, int optname, char *optval, int *optlen, bool getopt) @@ -5238,6 +5257,7 @@ static int sol_socket_sockopt(struct sock *sk, int optname, case SO_MAX_PACING_RATE: case SO_BINDTOIFINDEX: case SO_TXREHASH: + case SK_BPF_CB_FLAGS: if (*optlen != sizeof(int)) return -EINVAL; break; @@ -5247,6 +5267,9 @@ static int sol_socket_sockopt(struct sock *sk, int optname, return -EINVAL; } + if (optname == SK_BPF_CB_FLAGS) + return sk_bpf_set_get_cb_flags(sk, optval, getopt); + if (getopt) { if (optname == SO_BINDTODEVICE) return -EINVAL; @@ -5259,6 +5282,38 @@ static int sol_socket_sockopt(struct sock *sk, int optname, KERNEL_SOCKPTR(optval), *optlen); } +static int bpf_sol_tcp_getsockopt(struct sock *sk, int optname, + char *optval, int optlen) +{ + if (optlen != sizeof(int)) + return -EINVAL; + + switch (optname) { + case TCP_BPF_SOCK_OPS_CB_FLAGS: { + int cb_flags = tcp_sk(sk)->bpf_sock_ops_cb_flags; + + memcpy(optval, &cb_flags, optlen); + break; + } + case TCP_BPF_RTO_MIN: { + int rto_min_us = jiffies_to_usecs(inet_csk(sk)->icsk_rto_min); + + memcpy(optval, &rto_min_us, optlen); + break; + } + case TCP_BPF_DELACK_MAX: { + int delack_max_us = jiffies_to_usecs(inet_csk(sk)->icsk_delack_max); + + memcpy(optval, &delack_max_us, optlen); + break; + } + default: + return -EINVAL; + } + + return 0; +} + static int bpf_sol_tcp_setsockopt(struct sock *sk, int optname, char *optval, int optlen) { @@ -5382,6 +5437,7 @@ static int sol_tcp_sockopt(struct sock *sk, int optname, case TCP_USER_TIMEOUT: case TCP_NOTSENT_LOWAT: case TCP_SAVE_SYN: + case TCP_RTO_MAX_MS: if (*optlen != sizeof(int)) return -EINVAL; break; @@ -5391,20 +5447,9 @@ static int sol_tcp_sockopt(struct sock *sk, int optname, if (*optlen < 1) return -EINVAL; break; - case TCP_BPF_SOCK_OPS_CB_FLAGS: - if (*optlen != sizeof(int)) - return -EINVAL; - if (getopt) { - struct tcp_sock *tp = tcp_sk(sk); - int cb_flags = tp->bpf_sock_ops_cb_flags; - - memcpy(optval, &cb_flags, *optlen); - return 0; - } - return bpf_sol_tcp_setsockopt(sk, optname, optval, *optlen); default: if (getopt) - return -EINVAL; + return bpf_sol_tcp_getsockopt(sk, optname, optval, *optlen); return bpf_sol_tcp_setsockopt(sk, optname, optval, *optlen); } @@ -5500,6 +5545,11 @@ static int __bpf_setsockopt(struct sock *sk, int level, int optname, return -EINVAL; } +static bool is_locked_tcp_sock_ops(struct bpf_sock_ops_kern *bpf_sock) +{ + return bpf_sock->op <= BPF_SOCK_OPS_WRITE_HDR_OPT_CB; +} + static int _bpf_setsockopt(struct sock *sk, int level, int optname, char *optval, int optlen) { @@ -5650,6 +5700,9 @@ static const struct bpf_func_proto bpf_sock_addr_getsockopt_proto = { BPF_CALL_5(bpf_sock_ops_setsockopt, struct bpf_sock_ops_kern *, bpf_sock, int, level, int, optname, char *, optval, int, optlen) { + if (!is_locked_tcp_sock_ops(bpf_sock)) + return -EOPNOTSUPP; + return _bpf_setsockopt(bpf_sock->sk, level, optname, optval, optlen); } @@ -5735,6 +5788,9 @@ static int bpf_sock_ops_get_syn(struct bpf_sock_ops_kern *bpf_sock, BPF_CALL_5(bpf_sock_ops_getsockopt, struct bpf_sock_ops_kern *, bpf_sock, int, level, int, optname, char *, optval, int, optlen) { + if (!is_locked_tcp_sock_ops(bpf_sock)) + return -EOPNOTSUPP; + if (IS_ENABLED(CONFIG_INET) && level == SOL_TCP && optname >= TCP_BPF_SYN && optname <= TCP_BPF_SYN_MAC) { int ret, copy_len = 0; @@ -5777,6 +5833,9 @@ BPF_CALL_2(bpf_sock_ops_cb_flags_set, struct bpf_sock_ops_kern *, bpf_sock, struct sock *sk = bpf_sock->sk; int val = argval & BPF_SOCK_OPS_ALL_CB_FLAGS; + if (!is_locked_tcp_sock_ops(bpf_sock)) + return -EOPNOTSUPP; + if (!IS_ENABLED(CONFIG_INET) || !sk_fullsock(sk)) return -EINVAL; @@ -7586,6 +7645,9 @@ BPF_CALL_4(bpf_sock_ops_load_hdr_opt, struct bpf_sock_ops_kern *, bpf_sock, u8 search_kind, search_len, copy_len, magic_len; int ret; + if (!is_locked_tcp_sock_ops(bpf_sock)) + return -EOPNOTSUPP; + /* 2 byte is the minimal option len except TCPOPT_NOP and * TCPOPT_EOL which are useless for the bpf prog to learn * and this helper disallow loading them also. @@ -8075,6 +8137,8 @@ sk_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_skb_load_bytes_relative_proto; case BPF_FUNC_get_socket_cookie: return &bpf_get_socket_cookie_proto; + case BPF_FUNC_get_netns_cookie: + return &bpf_get_netns_cookie_proto; case BPF_FUNC_get_socket_uid: return &bpf_get_socket_uid_proto; case BPF_FUNC_perf_event_output: @@ -9635,7 +9699,7 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, case offsetof(struct __sk_buff, queue_mapping): if (type == BPF_WRITE) { - u32 off = bpf_target_off(struct sk_buff, queue_mapping, 2, target_size); + u32 offset = bpf_target_off(struct sk_buff, queue_mapping, 2, target_size); if (BPF_CLASS(si->code) == BPF_ST && si->imm >= NO_QUEUE_MAPPING) { *insn++ = BPF_JMP_A(0); /* noop */ @@ -9644,7 +9708,7 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, if (BPF_CLASS(si->code) == BPF_STX) *insn++ = BPF_JMP_IMM(BPF_JGE, si->src_reg, NO_QUEUE_MAPPING, 1); - *insn++ = BPF_EMIT_STORE(BPF_H, si, off); + *insn++ = BPF_EMIT_STORE(BPF_H, si, offset); } else { *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->src_reg, bpf_target_off(struct sk_buff, @@ -10358,10 +10422,10 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, } \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( \ struct bpf_sock_ops_kern, \ - is_fullsock), \ + is_locked_tcp_sock), \ fullsock_reg, si->src_reg, \ offsetof(struct bpf_sock_ops_kern, \ - is_fullsock)); \ + is_locked_tcp_sock)); \ *insn++ = BPF_JMP_IMM(BPF_JEQ, fullsock_reg, 0, jmp); \ if (si->dst_reg == si->src_reg) \ *insn++ = BPF_LDX_MEM(BPF_DW, reg, si->src_reg, \ @@ -10446,10 +10510,10 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, temp)); \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( \ struct bpf_sock_ops_kern, \ - is_fullsock), \ + is_locked_tcp_sock), \ reg, si->dst_reg, \ offsetof(struct bpf_sock_ops_kern, \ - is_fullsock)); \ + is_locked_tcp_sock)); \ *insn++ = BPF_JMP_IMM(BPF_JEQ, reg, 0, 2); \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( \ struct bpf_sock_ops_kern, sk),\ @@ -12062,6 +12126,25 @@ __bpf_kfunc int bpf_sk_assign_tcp_reqsk(struct __sk_buff *s, struct sock *sk, #endif } +__bpf_kfunc int bpf_sock_ops_enable_tx_tstamp(struct bpf_sock_ops_kern *skops, + u64 flags) +{ + struct sk_buff *skb; + + if (skops->op != BPF_SOCK_OPS_TSTAMP_SENDMSG_CB) + return -EOPNOTSUPP; + + if (flags) + return -EINVAL; + + skb = skops->skb; + skb_shinfo(skb)->tx_flags |= SKBTX_BPF; + TCP_SKB_CB(skb)->txstamp_ack |= TSTAMP_ACK_BPF; + skb_shinfo(skb)->tskey = TCP_SKB_CB(skb)->seq + skb->len - 1; + + return 0; +} + __bpf_kfunc_end_defs(); int bpf_dynptr_from_skb_rdonly(struct __sk_buff *skb, u64 flags, @@ -12095,6 +12178,10 @@ BTF_KFUNCS_START(bpf_kfunc_check_set_tcp_reqsk) BTF_ID_FLAGS(func, bpf_sk_assign_tcp_reqsk, KF_TRUSTED_ARGS) BTF_KFUNCS_END(bpf_kfunc_check_set_tcp_reqsk) +BTF_KFUNCS_START(bpf_kfunc_check_set_sock_ops) +BTF_ID_FLAGS(func, bpf_sock_ops_enable_tx_tstamp, KF_TRUSTED_ARGS) +BTF_KFUNCS_END(bpf_kfunc_check_set_sock_ops) + static const struct btf_kfunc_id_set bpf_kfunc_set_skb = { .owner = THIS_MODULE, .set = &bpf_kfunc_check_set_skb, @@ -12115,6 +12202,11 @@ static const struct btf_kfunc_id_set bpf_kfunc_set_tcp_reqsk = { .set = &bpf_kfunc_check_set_tcp_reqsk, }; +static const struct btf_kfunc_id_set bpf_kfunc_set_sock_ops = { + .owner = THIS_MODULE, + .set = &bpf_kfunc_check_set_sock_ops, +}; + static int __init bpf_kfunc_init(void) { int ret; @@ -12133,7 +12225,8 @@ static int __init bpf_kfunc_init(void) ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_XDP, &bpf_kfunc_set_xdp); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_CGROUP_SOCK_ADDR, &bpf_kfunc_set_sock_addr); - return ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS, &bpf_kfunc_set_tcp_reqsk); + ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS, &bpf_kfunc_set_tcp_reqsk); + return ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SOCK_OPS, &bpf_kfunc_set_sock_ops); } late_initcall(bpf_kfunc_init); diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 0e638a37aa09..1b61bb25ba0e 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -106,7 +106,7 @@ int flow_dissector_bpf_prog_attach_check(struct net *net, #endif /* CONFIG_BPF_SYSCALL */ /** - * __skb_flow_get_ports - extract the upper layer ports and return them + * skb_flow_get_ports - extract the upper layer ports and return them * @skb: sk_buff to extract the ports from * @thoff: transport header offset * @ip_proto: protocol for which to get port offset @@ -116,8 +116,8 @@ int flow_dissector_bpf_prog_attach_check(struct net *net, * The function will try to retrieve the ports at offset thoff + poff where poff * is the protocol port offset returned from proto_ports_offset */ -__be32 __skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto, - const void *data, int hlen) +__be32 skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto, + const void *data, int hlen) { int poff = proto_ports_offset(ip_proto); @@ -137,7 +137,7 @@ __be32 __skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto, return 0; } -EXPORT_SYMBOL(__skb_flow_get_ports); +EXPORT_SYMBOL(skb_flow_get_ports); static bool icmp_has_id(u8 type) { @@ -853,23 +853,30 @@ __skb_flow_dissect_ports(const struct sk_buff *skb, void *target_container, const void *data, int nhoff, u8 ip_proto, int hlen) { - enum flow_dissector_key_id dissector_ports = FLOW_DISSECTOR_KEY_MAX; - struct flow_dissector_key_ports *key_ports; + struct flow_dissector_key_ports_range *key_ports_range = NULL; + struct flow_dissector_key_ports *key_ports = NULL; + __be32 ports; if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_PORTS)) - dissector_ports = FLOW_DISSECTOR_KEY_PORTS; - else if (dissector_uses_key(flow_dissector, - FLOW_DISSECTOR_KEY_PORTS_RANGE)) - dissector_ports = FLOW_DISSECTOR_KEY_PORTS_RANGE; + key_ports = skb_flow_dissector_target(flow_dissector, + FLOW_DISSECTOR_KEY_PORTS, + target_container); + + if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_PORTS_RANGE)) + key_ports_range = skb_flow_dissector_target(flow_dissector, + FLOW_DISSECTOR_KEY_PORTS_RANGE, + target_container); - if (dissector_ports == FLOW_DISSECTOR_KEY_MAX) + if (!key_ports && !key_ports_range) return; - key_ports = skb_flow_dissector_target(flow_dissector, - dissector_ports, - target_container); - key_ports->ports = __skb_flow_get_ports(skb, nhoff, ip_proto, - data, hlen); + ports = skb_flow_get_ports(skb, nhoff, ip_proto, data, hlen); + + if (key_ports) + key_ports->ports = ports; + + if (key_ports_range) + key_ports_range->tp.ports = ports; } static void @@ -924,6 +931,7 @@ static void __skb_flow_bpf_to_target(const struct bpf_flow_keys *flow_keys, struct flow_dissector *flow_dissector, void *target_container) { + struct flow_dissector_key_ports_range *key_ports_range = NULL; struct flow_dissector_key_ports *key_ports = NULL; struct flow_dissector_key_control *key_control; struct flow_dissector_key_basic *key_basic; @@ -968,20 +976,21 @@ static void __skb_flow_bpf_to_target(const struct bpf_flow_keys *flow_keys, key_control->addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; } - if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_PORTS)) + if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_PORTS)) { key_ports = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_PORTS, target_container); - else if (dissector_uses_key(flow_dissector, - FLOW_DISSECTOR_KEY_PORTS_RANGE)) - key_ports = skb_flow_dissector_target(flow_dissector, - FLOW_DISSECTOR_KEY_PORTS_RANGE, - target_container); - - if (key_ports) { key_ports->src = flow_keys->sport; key_ports->dst = flow_keys->dport; } + if (dissector_uses_key(flow_dissector, + FLOW_DISSECTOR_KEY_PORTS_RANGE)) { + key_ports_range = skb_flow_dissector_target(flow_dissector, + FLOW_DISSECTOR_KEY_PORTS_RANGE, + target_container); + key_ports_range->tp.src = flow_keys->sport; + key_ports_range->tp.dst = flow_keys->dport; + } if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_FLOW_LABEL)) { @@ -1108,10 +1117,12 @@ bool __skb_flow_dissect(const struct net *net, FLOW_DISSECTOR_KEY_BASIC, target_container); + rcu_read_lock(); + if (skb) { if (!net) { if (skb->dev) - net = dev_net(skb->dev); + net = dev_net_rcu(skb->dev); else if (skb->sk) net = sock_net(skb->sk); } @@ -1122,7 +1133,6 @@ bool __skb_flow_dissect(const struct net *net, enum netns_bpf_attach_type type = NETNS_BPF_FLOW_DISSECTOR; struct bpf_prog_array *run_array; - rcu_read_lock(); run_array = rcu_dereference(init_net.bpf.run_array[type]); if (!run_array) run_array = rcu_dereference(net->bpf.run_array[type]); @@ -1150,17 +1160,17 @@ bool __skb_flow_dissect(const struct net *net, prog = READ_ONCE(run_array->items[0].prog); result = bpf_flow_dissect(prog, &ctx, n_proto, nhoff, hlen, flags); - if (result == BPF_FLOW_DISSECTOR_CONTINUE) - goto dissect_continue; - __skb_flow_bpf_to_target(&flow_keys, flow_dissector, - target_container); - rcu_read_unlock(); - return result == BPF_OK; + if (result != BPF_FLOW_DISSECTOR_CONTINUE) { + __skb_flow_bpf_to_target(&flow_keys, flow_dissector, + target_container); + rcu_read_unlock(); + return result == BPF_OK; + } } -dissect_continue: - rcu_read_unlock(); } + rcu_read_unlock(); + if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ETH_ADDRS)) { struct ethhdr *eth = eth_hdr(skb); diff --git a/net/core/gen_estimator.c b/net/core/gen_estimator.c index 412816076b8b..2b821b9a8699 100644 --- a/net/core/gen_estimator.c +++ b/net/core/gen_estimator.c @@ -177,7 +177,7 @@ int gen_new_estimator(struct gnet_stats_basic_sync *bstats, spin_lock_bh(lock); old = rcu_dereference_protected(*rate_est, 1); if (old) { - del_timer_sync(&old->timer); + timer_delete_sync(&old->timer); est->avbps = old->avbps; est->avpps = old->avpps; } diff --git a/net/core/gro.c b/net/core/gro.c index d1f44084e978..b350e5b69549 100644 --- a/net/core/gro.c +++ b/net/core/gro.c @@ -7,9 +7,6 @@ #define MAX_GRO_SKBS 8 -/* This should be increased if a protocol with a bigger head is added. */ -#define GRO_MAX_HEAD (MAX_HEADER + 128) - static DEFINE_SPINLOCK(offload_lock); /** @@ -253,8 +250,7 @@ int skb_gro_receive_list(struct sk_buff *p, struct sk_buff *skb) return 0; } - -static void napi_gro_complete(struct napi_struct *napi, struct sk_buff *skb) +static void gro_complete(struct gro_node *gro, struct sk_buff *skb) { struct list_head *head = &net_hotdata.offload_base; struct packet_offload *ptype; @@ -287,43 +283,43 @@ static void napi_gro_complete(struct napi_struct *napi, struct sk_buff *skb) } out: - gro_normal_one(napi, skb, NAPI_GRO_CB(skb)->count); + gro_normal_one(gro, skb, NAPI_GRO_CB(skb)->count); } -static void __napi_gro_flush_chain(struct napi_struct *napi, u32 index, - bool flush_old) +static void __gro_flush_chain(struct gro_node *gro, u32 index, bool flush_old) { - struct list_head *head = &napi->gro_hash[index].list; + struct list_head *head = &gro->hash[index].list; struct sk_buff *skb, *p; list_for_each_entry_safe_reverse(skb, p, head, list) { if (flush_old && NAPI_GRO_CB(skb)->age == jiffies) return; skb_list_del_init(skb); - napi_gro_complete(napi, skb); - napi->gro_hash[index].count--; + gro_complete(gro, skb); + gro->hash[index].count--; } - if (!napi->gro_hash[index].count) - __clear_bit(index, &napi->gro_bitmask); + if (!gro->hash[index].count) + __clear_bit(index, &gro->bitmask); } -/* napi->gro_hash[].list contains packets ordered by age. +/* + * gro->hash[].list contains packets ordered by age. * youngest packets at the head of it. * Complete skbs in reverse order to reduce latencies. */ -void napi_gro_flush(struct napi_struct *napi, bool flush_old) +void __gro_flush(struct gro_node *gro, bool flush_old) { - unsigned long bitmask = napi->gro_bitmask; + unsigned long bitmask = gro->bitmask; unsigned int i, base = ~0U; while ((i = ffs(bitmask)) != 0) { bitmask >>= i; base += i; - __napi_gro_flush_chain(napi, base, flush_old); + __gro_flush_chain(gro, base, flush_old); } } -EXPORT_SYMBOL(napi_gro_flush); +EXPORT_SYMBOL(__gro_flush); static unsigned long gro_list_prepare_tc_ext(const struct sk_buff *skb, const struct sk_buff *p, @@ -442,7 +438,7 @@ static void gro_try_pull_from_frag0(struct sk_buff *skb) gro_pull_from_frag0(skb, grow); } -static void gro_flush_oldest(struct napi_struct *napi, struct list_head *head) +static void gro_flush_oldest(struct gro_node *gro, struct list_head *head) { struct sk_buff *oldest; @@ -458,14 +454,15 @@ static void gro_flush_oldest(struct napi_struct *napi, struct list_head *head) * SKB to the chain. */ skb_list_del_init(oldest); - napi_gro_complete(napi, oldest); + gro_complete(gro, oldest); } -static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb) +static enum gro_result dev_gro_receive(struct gro_node *gro, + struct sk_buff *skb) { u32 bucket = skb_get_hash_raw(skb) & (GRO_HASH_BUCKETS - 1); - struct gro_list *gro_list = &napi->gro_hash[bucket]; struct list_head *head = &net_hotdata.offload_base; + struct gro_list *gro_list = &gro->hash[bucket]; struct packet_offload *ptype; __be16 type = skb->protocol; struct sk_buff *pp = NULL; @@ -529,7 +526,7 @@ found_ptype: if (pp) { skb_list_del_init(pp); - napi_gro_complete(napi, pp); + gro_complete(gro, pp); gro_list->count--; } @@ -540,7 +537,7 @@ found_ptype: goto normal; if (unlikely(gro_list->count >= MAX_GRO_SKBS)) - gro_flush_oldest(napi, &gro_list->list); + gro_flush_oldest(gro, &gro_list->list); else gro_list->count++; @@ -554,10 +551,10 @@ found_ptype: ret = GRO_HELD; ok: if (gro_list->count) { - if (!test_bit(bucket, &napi->gro_bitmask)) - __set_bit(bucket, &napi->gro_bitmask); - } else if (test_bit(bucket, &napi->gro_bitmask)) { - __clear_bit(bucket, &napi->gro_bitmask); + if (!test_bit(bucket, &gro->bitmask)) + __set_bit(bucket, &gro->bitmask); + } else if (test_bit(bucket, &gro->bitmask)) { + __clear_bit(bucket, &gro->bitmask); } return ret; @@ -596,13 +593,12 @@ struct packet_offload *gro_find_complete_by_type(__be16 type) } EXPORT_SYMBOL(gro_find_complete_by_type); -static gro_result_t napi_skb_finish(struct napi_struct *napi, - struct sk_buff *skb, - gro_result_t ret) +static gro_result_t gro_skb_finish(struct gro_node *gro, struct sk_buff *skb, + gro_result_t ret) { switch (ret) { case GRO_NORMAL: - gro_normal_one(napi, skb, 1); + gro_normal_one(gro, skb, 1); break; case GRO_MERGED_FREE: @@ -623,21 +619,21 @@ static gro_result_t napi_skb_finish(struct napi_struct *napi, return ret; } -gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb) +gro_result_t gro_receive_skb(struct gro_node *gro, struct sk_buff *skb) { gro_result_t ret; - skb_mark_napi_id(skb, napi); + __skb_mark_napi_id(skb, gro); trace_napi_gro_receive_entry(skb); skb_gro_reset_offset(skb, 0); - ret = napi_skb_finish(napi, skb, dev_gro_receive(napi, skb)); + ret = gro_skb_finish(gro, skb, dev_gro_receive(gro, skb)); trace_napi_gro_receive_exit(ret); return ret; } -EXPORT_SYMBOL(napi_gro_receive); +EXPORT_SYMBOL(gro_receive_skb); static void napi_reuse_skb(struct napi_struct *napi, struct sk_buff *skb) { @@ -656,6 +652,7 @@ static void napi_reuse_skb(struct napi_struct *napi, struct sk_buff *skb) skb->pkt_type = PACKET_HOST; skb->encapsulation = 0; + skb->ip_summed = CHECKSUM_NONE; skb_shinfo(skb)->gso_type = 0; skb_shinfo(skb)->gso_size = 0; if (unlikely(skb->slow_gro)) { @@ -693,7 +690,7 @@ static gro_result_t napi_frags_finish(struct napi_struct *napi, __skb_push(skb, ETH_HLEN); skb->protocol = eth_type_trans(skb, skb->dev); if (ret == GRO_NORMAL) - gro_normal_one(napi, skb, 1); + gro_normal_one(&napi->gro, skb, 1); break; case GRO_MERGED_FREE: @@ -762,7 +759,7 @@ gro_result_t napi_gro_frags(struct napi_struct *napi) trace_napi_gro_frags_entry(skb); - ret = napi_frags_finish(napi, skb, dev_gro_receive(napi, skb)); + ret = napi_frags_finish(napi, skb, dev_gro_receive(&napi->gro, skb)); trace_napi_gro_frags_exit(ret); return ret; @@ -794,3 +791,37 @@ __sum16 __skb_gro_checksum_complete(struct sk_buff *skb) return sum; } EXPORT_SYMBOL(__skb_gro_checksum_complete); + +void gro_init(struct gro_node *gro) +{ + for (u32 i = 0; i < GRO_HASH_BUCKETS; i++) { + INIT_LIST_HEAD(&gro->hash[i].list); + gro->hash[i].count = 0; + } + + gro->bitmask = 0; + gro->cached_napi_id = 0; + + INIT_LIST_HEAD(&gro->rx_list); + gro->rx_count = 0; +} + +void gro_cleanup(struct gro_node *gro) +{ + struct sk_buff *skb, *n; + + for (u32 i = 0; i < GRO_HASH_BUCKETS; i++) { + list_for_each_entry_safe(skb, n, &gro->hash[i].list, list) + kfree_skb(skb); + + gro->hash[i].count = 0; + } + + gro->bitmask = 0; + gro->cached_napi_id = 0; + + list_for_each_entry_safe(skb, n, &gro->rx_list, list) + kfree_skb(skb); + + gro->rx_count = 0; +} diff --git a/net/core/hotdata.c b/net/core/hotdata.c index d0aaaaa556f2..0bc893d5f07b 100644 --- a/net/core/hotdata.c +++ b/net/core/hotdata.c @@ -7,7 +7,6 @@ struct net_hotdata net_hotdata __cacheline_aligned = { .offload_base = LIST_HEAD_INIT(net_hotdata.offload_base), - .ptype_all = LIST_HEAD_INIT(net_hotdata.ptype_all), .gro_normal_batch = 8, .netdev_budget = 300, diff --git a/net/core/rtnl_net_debug.c b/net/core/lock_debug.c index 7ecd28cc1c22..b7f22dc92a6f 100644 --- a/net/core/rtnl_net_debug.c +++ b/net/core/lock_debug.c @@ -6,10 +6,11 @@ #include <linux/notifier.h> #include <linux/rtnetlink.h> #include <net/net_namespace.h> +#include <net/netdev_lock.h> #include <net/netns/generic.h> -static int rtnl_net_debug_event(struct notifier_block *nb, - unsigned long event, void *ptr) +int netdev_debug_event(struct notifier_block *nb, unsigned long event, + void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct net *net = dev_net(dev); @@ -17,11 +18,13 @@ static int rtnl_net_debug_event(struct notifier_block *nb, /* Keep enum and don't add default to trigger -Werror=switch */ switch (cmd) { + case NETDEV_REGISTER: case NETDEV_UP: + netdev_ops_assert_locked(dev); + fallthrough; case NETDEV_DOWN: case NETDEV_REBOOT: case NETDEV_CHANGE: - case NETDEV_REGISTER: case NETDEV_UNREGISTER: case NETDEV_CHANGEMTU: case NETDEV_CHANGEADDR: @@ -66,6 +69,7 @@ static int rtnl_net_debug_event(struct notifier_block *nb, return NOTIFY_DONE; } +EXPORT_SYMBOL_NS_GPL(netdev_debug_event, "NETDEV_INTERNAL"); static int rtnl_net_debug_net_id; @@ -74,7 +78,7 @@ static int __net_init rtnl_net_debug_net_init(struct net *net) struct notifier_block *nb; nb = net_generic(net, rtnl_net_debug_net_id); - nb->notifier_call = rtnl_net_debug_event; + nb->notifier_call = netdev_debug_event; return register_netdevice_notifier_net(net, nb); } @@ -95,14 +99,14 @@ static struct pernet_operations rtnl_net_debug_net_ops __net_initdata = { }; static struct notifier_block rtnl_net_debug_block = { - .notifier_call = rtnl_net_debug_event, + .notifier_call = netdev_debug_event, }; static int __init rtnl_net_debug_init(void) { int ret; - ret = register_pernet_device(&rtnl_net_debug_net_ops); + ret = register_pernet_subsys(&rtnl_net_debug_net_ops); if (ret) return ret; diff --git a/net/core/lwtunnel.c b/net/core/lwtunnel.c index 711cd3b4347a..e39a459540ec 100644 --- a/net/core/lwtunnel.c +++ b/net/core/lwtunnel.c @@ -23,6 +23,8 @@ #include <net/ip6_fib.h> #include <net/rtnh.h> +#include "dev.h" + DEFINE_STATIC_KEY_FALSE(nf_hooks_lwtunnel_enabled); EXPORT_SYMBOL_GPL(nf_hooks_lwtunnel_enabled); @@ -147,7 +149,8 @@ int lwtunnel_build_state(struct net *net, u16 encap_type, } EXPORT_SYMBOL_GPL(lwtunnel_build_state); -int lwtunnel_valid_encap_type(u16 encap_type, struct netlink_ext_ack *extack) +int lwtunnel_valid_encap_type(u16 encap_type, struct netlink_ext_ack *extack, + bool rtnl_is_held) { const struct lwtunnel_encap_ops *ops; int ret = -EINVAL; @@ -158,21 +161,19 @@ int lwtunnel_valid_encap_type(u16 encap_type, struct netlink_ext_ack *extack) return ret; } - rcu_read_lock(); - ops = rcu_dereference(lwtun_encaps[encap_type]); - rcu_read_unlock(); + ops = rcu_access_pointer(lwtun_encaps[encap_type]); #ifdef CONFIG_MODULES if (!ops) { const char *encap_type_str = lwtunnel_encap_str(encap_type); if (encap_type_str) { - __rtnl_unlock(); + if (rtnl_is_held) + __rtnl_unlock(); request_module("rtnl-lwt-%s", encap_type_str); - rtnl_lock(); + if (rtnl_is_held) + rtnl_lock(); - rcu_read_lock(); - ops = rcu_dereference(lwtun_encaps[encap_type]); - rcu_read_unlock(); + ops = rcu_access_pointer(lwtun_encaps[encap_type]); } } #endif @@ -185,7 +186,8 @@ int lwtunnel_valid_encap_type(u16 encap_type, struct netlink_ext_ack *extack) EXPORT_SYMBOL_GPL(lwtunnel_valid_encap_type); int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int remaining, - struct netlink_ext_ack *extack) + struct netlink_ext_ack *extack, + bool rtnl_is_held) { struct rtnexthop *rtnh = (struct rtnexthop *)attr; struct nlattr *nla_entype; @@ -207,7 +209,8 @@ int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int remaining, encap_type = nla_get_u16(nla_entype); if (lwtunnel_valid_encap_type(encap_type, - extack) != 0) + extack, + rtnl_is_held) != 0) return -EOPNOTSUPP; } } @@ -325,13 +328,23 @@ EXPORT_SYMBOL_GPL(lwtunnel_cmp_encap); int lwtunnel_output(struct net *net, struct sock *sk, struct sk_buff *skb) { - struct dst_entry *dst = skb_dst(skb); const struct lwtunnel_encap_ops *ops; struct lwtunnel_state *lwtstate; - int ret = -EINVAL; + struct dst_entry *dst; + int ret; - if (!dst) + if (dev_xmit_recursion()) { + net_crit_ratelimited("%s(): recursion limit reached on datapath\n", + __func__); + ret = -ENETDOWN; goto drop; + } + + dst = skb_dst(skb); + if (!dst) { + ret = -EINVAL; + goto drop; + } lwtstate = dst->lwtstate; if (lwtstate->type == LWTUNNEL_ENCAP_NONE || @@ -341,8 +354,11 @@ int lwtunnel_output(struct net *net, struct sock *sk, struct sk_buff *skb) ret = -EOPNOTSUPP; rcu_read_lock(); ops = rcu_dereference(lwtun_encaps[lwtstate->type]); - if (likely(ops && ops->output)) + if (likely(ops && ops->output)) { + dev_xmit_recursion_inc(); ret = ops->output(net, sk, skb); + dev_xmit_recursion_dec(); + } rcu_read_unlock(); if (ret == -EOPNOTSUPP) @@ -359,13 +375,23 @@ EXPORT_SYMBOL_GPL(lwtunnel_output); int lwtunnel_xmit(struct sk_buff *skb) { - struct dst_entry *dst = skb_dst(skb); const struct lwtunnel_encap_ops *ops; struct lwtunnel_state *lwtstate; - int ret = -EINVAL; + struct dst_entry *dst; + int ret; - if (!dst) + if (dev_xmit_recursion()) { + net_crit_ratelimited("%s(): recursion limit reached on datapath\n", + __func__); + ret = -ENETDOWN; goto drop; + } + + dst = skb_dst(skb); + if (!dst) { + ret = -EINVAL; + goto drop; + } lwtstate = dst->lwtstate; @@ -376,8 +402,11 @@ int lwtunnel_xmit(struct sk_buff *skb) ret = -EOPNOTSUPP; rcu_read_lock(); ops = rcu_dereference(lwtun_encaps[lwtstate->type]); - if (likely(ops && ops->xmit)) + if (likely(ops && ops->xmit)) { + dev_xmit_recursion_inc(); ret = ops->xmit(skb); + dev_xmit_recursion_dec(); + } rcu_read_unlock(); if (ret == -EOPNOTSUPP) @@ -394,13 +423,23 @@ EXPORT_SYMBOL_GPL(lwtunnel_xmit); int lwtunnel_input(struct sk_buff *skb) { - struct dst_entry *dst = skb_dst(skb); const struct lwtunnel_encap_ops *ops; struct lwtunnel_state *lwtstate; - int ret = -EINVAL; + struct dst_entry *dst; + int ret; + + if (dev_xmit_recursion()) { + net_crit_ratelimited("%s(): recursion limit reached on datapath\n", + __func__); + ret = -ENETDOWN; + goto drop; + } - if (!dst) + dst = skb_dst(skb); + if (!dst) { + ret = -EINVAL; goto drop; + } lwtstate = dst->lwtstate; if (lwtstate->type == LWTUNNEL_ENCAP_NONE || @@ -410,8 +449,11 @@ int lwtunnel_input(struct sk_buff *skb) ret = -EOPNOTSUPP; rcu_read_lock(); ops = rcu_dereference(lwtun_encaps[lwtstate->type]); - if (likely(ops && ops->input)) + if (likely(ops && ops->input)) { + dev_xmit_recursion_inc(); ret = ops->input(skb); + dev_xmit_recursion_dec(); + } rcu_read_unlock(); if (ret == -EOPNOTSUPP) diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 89656d180bc6..a07249b59ae1 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -309,7 +309,7 @@ static void neigh_add_timer(struct neighbour *n, unsigned long when) static int neigh_del_timer(struct neighbour *n) { if ((n->nud_state & NUD_IN_TIMER) && - del_timer(&n->timer)) { + timer_delete(&n->timer)) { neigh_release(n); return 1; } @@ -427,7 +427,7 @@ static int __neigh_ifdown(struct neigh_table *tbl, struct net_device *dev, pneigh_queue_purge(&tbl->proxy_queue, dev ? dev_net(dev) : NULL, tbl->family); if (skb_queue_empty_lockless(&tbl->proxy_queue)) - del_timer_sync(&tbl->proxy_timer); + timer_delete_sync(&tbl->proxy_timer); return 0; } @@ -518,7 +518,7 @@ static struct neigh_hash_table *neigh_hash_alloc(unsigned int shift) if (!ret) return NULL; - hash_heads = kvzalloc(size, GFP_ATOMIC); + hash_heads = kzalloc(size, GFP_ATOMIC); if (!hash_heads) { kfree(ret); return NULL; @@ -536,7 +536,7 @@ static void neigh_hash_free_rcu(struct rcu_head *head) struct neigh_hash_table, rcu); - kvfree(nht->hash_heads); + kfree(nht->hash_heads); kfree(nht); } @@ -832,12 +832,10 @@ static int pneigh_ifdown_and_unlock(struct neigh_table *tbl, return -ENOENT; } -static void neigh_parms_destroy(struct neigh_parms *parms); - static inline void neigh_parms_put(struct neigh_parms *parms) { if (refcount_dec_and_test(&parms->refcnt)) - neigh_parms_destroy(parms); + kfree(parms); } /* @@ -1599,7 +1597,7 @@ static void neigh_proxy_process(struct timer_list *t) } else if (!sched_next || tdif < sched_next) sched_next = tdif; } - del_timer(&tbl->proxy_timer); + timer_delete(&tbl->proxy_timer); if (sched_next) mod_timer(&tbl->proxy_timer, jiffies + sched_next); spin_unlock(&tbl->proxy_queue.lock); @@ -1630,7 +1628,7 @@ void pneigh_enqueue(struct neigh_table *tbl, struct neigh_parms *p, NEIGH_CB(skb)->flags |= LOCALLY_ENQUEUED; spin_lock(&tbl->proxy_queue.lock); - if (del_timer(&tbl->proxy_timer)) { + if (timer_delete(&tbl->proxy_timer)) { if (time_before(tbl->proxy_timer.expires, sched_next)) sched_next = tbl->proxy_timer.expires; } @@ -1713,11 +1711,6 @@ void neigh_parms_release(struct neigh_table *tbl, struct neigh_parms *parms) } EXPORT_SYMBOL(neigh_parms_release); -static void neigh_parms_destroy(struct neigh_parms *parms) -{ - kfree(parms); -} - static struct lock_class_key neigh_table_proxy_queue_class; static struct neigh_table __rcu *neigh_tables[NEIGH_NR_TABLES] __read_mostly; @@ -1793,7 +1786,7 @@ int neigh_table_clear(int index, struct neigh_table *tbl) /* It is not clean... Fix it to unload IPv6 module safely */ cancel_delayed_work_sync(&tbl->managed_work); cancel_delayed_work_sync(&tbl->gc_work); - del_timer_sync(&tbl->proxy_timer); + timer_delete_sync(&tbl->proxy_timer); pneigh_queue_purge(&tbl->proxy_queue, NULL, tbl->family); neigh_ifdown(tbl, NULL); if (atomic_read(&tbl->entries)) @@ -2250,6 +2243,7 @@ static const struct nla_policy nl_neightbl_policy[NDTA_MAX+1] = { static const struct nla_policy nl_ntbl_parm_policy[NDTPA_MAX+1] = { [NDTPA_IFINDEX] = { .type = NLA_U32 }, [NDTPA_QUEUE_LEN] = { .type = NLA_U32 }, + [NDTPA_QUEUE_LENBYTES] = { .type = NLA_U32 }, [NDTPA_PROXY_QLEN] = { .type = NLA_U32 }, [NDTPA_APP_PROBES] = { .type = NLA_U32 }, [NDTPA_UCAST_PROBES] = { .type = NLA_U32 }, @@ -3447,10 +3441,12 @@ static const struct seq_operations neigh_stat_seq_ops = { static void __neigh_notify(struct neighbour *n, int type, int flags, u32 pid) { - struct net *net = dev_net(n->dev); struct sk_buff *skb; int err = -ENOBUFS; + struct net *net; + rcu_read_lock(); + net = dev_net_rcu(n->dev); skb = nlmsg_new(neigh_nlmsg_size(), GFP_ATOMIC); if (skb == NULL) goto errout; @@ -3463,9 +3459,11 @@ static void __neigh_notify(struct neighbour *n, int type, int flags, goto errout; } rtnl_notify(skb, net, 0, RTNLGRP_NEIGH, NULL, GFP_ATOMIC); - return; + goto out; errout: rtnl_set_sk_err(net, RTNLGRP_NEIGH, err); +out: + rcu_read_unlock(); } void neigh_app_ns(struct neighbour *n) diff --git a/net/core/net-procfs.c b/net/core/net-procfs.c index fa6d3969734a..3e92bf0f9060 100644 --- a/net/core/net-procfs.c +++ b/net/core/net-procfs.c @@ -185,7 +185,13 @@ static void *ptype_get_idx(struct seq_file *seq, loff_t pos) } } - list_for_each_entry_rcu(pt, &net_hotdata.ptype_all, list) { + list_for_each_entry_rcu(pt, &seq_file_net(seq)->ptype_all, list) { + if (i == pos) + return pt; + ++i; + } + + list_for_each_entry_rcu(pt, &seq_file_net(seq)->ptype_specific, list) { if (i == pos) return pt; ++i; @@ -210,6 +216,7 @@ static void *ptype_seq_start(struct seq_file *seq, loff_t *pos) static void *ptype_seq_next(struct seq_file *seq, void *v, loff_t *pos) { + struct net *net = seq_file_net(seq); struct net_device *dev; struct packet_type *pt; struct list_head *nxt; @@ -232,15 +239,22 @@ static void *ptype_seq_next(struct seq_file *seq, void *v, loff_t *pos) goto found; } } - - nxt = net_hotdata.ptype_all.next; - goto ptype_all; + nxt = net->ptype_all.next; + goto net_ptype_all; } - if (pt->type == htons(ETH_P_ALL)) { -ptype_all: - if (nxt != &net_hotdata.ptype_all) + if (pt->af_packet_net) { +net_ptype_all: + if (nxt != &net->ptype_all && nxt != &net->ptype_specific) goto found; + + if (nxt == &net->ptype_all) { + /* continue with ->ptype_specific if it's not empty */ + nxt = net->ptype_specific.next; + if (nxt != &net->ptype_specific) + goto found; + } + hash = 0; nxt = ptype_base[0].next; } else diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 07cb99b114bd..1ace0cd01adc 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -23,6 +23,7 @@ #include <linux/of.h> #include <linux/of_net.h> #include <linux/cpu.h> +#include <net/netdev_lock.h> #include <net/netdev_rx_queue.h> #include <net/rps.h> @@ -42,6 +43,87 @@ static inline int dev_isalive(const struct net_device *dev) return READ_ONCE(dev->reg_state) <= NETREG_REGISTERED; } +/* There is a possible ABBA deadlock between rtnl_lock and kernfs_node->active, + * when unregistering a net device and accessing associated sysfs files. The + * potential deadlock is as follow: + * + * CPU 0 CPU 1 + * + * rtnl_lock vfs_read + * unregister_netdevice_many kernfs_seq_start + * device_del / kobject_put kernfs_get_active (kn->active++) + * kernfs_drain sysfs_kf_seq_show + * wait_event( rtnl_lock + * kn->active == KN_DEACTIVATED_BIAS) -> waits on CPU 0 to release + * -> waits on CPU 1 to decrease kn->active the rtnl lock. + * + * The historical fix was to use rtnl_trylock with restart_syscall to bail out + * of sysfs operations when the lock couldn't be taken. This fixed the above + * issue as it allowed CPU 1 to bail out of the ABBA situation. + * + * But it came with performances issues, as syscalls are being restarted in + * loops when there was contention on the rtnl lock, with huge slow downs in + * specific scenarios (e.g. lots of virtual interfaces created and userspace + * daemons querying their attributes). + * + * The idea below is to bail out of the active kernfs_node protection + * (kn->active) while trying to take the rtnl lock. + * + * This replaces rtnl_lock() and still has to be used with rtnl_unlock(). The + * net device is guaranteed to be alive if this returns successfully. + */ +static int sysfs_rtnl_lock(struct kobject *kobj, struct attribute *attr, + struct net_device *ndev) +{ + struct kernfs_node *kn; + int ret = 0; + + /* First, we hold a reference to the net device as the unregistration + * path might run in parallel. This will ensure the net device and the + * associated sysfs objects won't be freed while we try to take the rtnl + * lock. + */ + dev_hold(ndev); + /* sysfs_break_active_protection was introduced to allow self-removal of + * devices and their associated sysfs files by bailing out of the + * sysfs/kernfs protection. We do this here to allow the unregistration + * path to complete in parallel. The following takes a reference on the + * kobject and the kernfs_node being accessed. + * + * This works because we hold a reference onto the net device and the + * unregistration path will wait for us eventually in netdev_run_todo + * (outside an rtnl lock section). + */ + kn = sysfs_break_active_protection(kobj, attr); + /* We can now try to take the rtnl lock. This can't deadlock us as the + * unregistration path is able to drain sysfs files (kernfs_node) thanks + * to the above dance. + */ + if (rtnl_lock_interruptible()) { + ret = -ERESTARTSYS; + goto unbreak; + } + /* Check dismantle on the device hasn't started, otherwise deny the + * operation. + */ + if (!dev_isalive(ndev)) { + rtnl_unlock(); + ret = -ENODEV; + goto unbreak; + } + /* We are now sure the device dismantle hasn't started nor that it can + * start before we exit the locking section as we hold the rtnl lock. + * There's no need to keep unbreaking the sysfs protection nor to hold + * a net device reference from that point; that was only needed to take + * the rtnl lock. + */ +unbreak: + sysfs_unbreak_active_protection(kn); + dev_put(ndev); + + return ret; +} + /* use same locking rules as GIF* ioctl's */ static ssize_t netdev_show(const struct device *dev, struct device_attribute *attr, char *buf, @@ -95,14 +177,14 @@ static ssize_t netdev_store(struct device *dev, struct device_attribute *attr, if (ret) goto err; - if (!rtnl_trylock()) - return restart_syscall(); + ret = sysfs_rtnl_lock(&dev->kobj, &attr->attr, netdev); + if (ret) + goto err; + + ret = (*set)(netdev, new); + if (ret == 0) + ret = len; - if (dev_isalive(netdev)) { - ret = (*set)(netdev, new); - if (ret == 0) - ret = len; - } rtnl_unlock(); err: return ret; @@ -220,7 +302,7 @@ static ssize_t carrier_store(struct device *dev, struct device_attribute *attr, struct net_device *netdev = to_net_dev(dev); /* The check is also done in change_carrier; this helps returning early - * without hitting the trylock/restart in netdev_store. + * without hitting the locking section in netdev_store. */ if (!netdev->netdev_ops->ndo_change_carrier) return -EOPNOTSUPP; @@ -232,11 +314,13 @@ 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; + int ret; - if (!rtnl_trylock()) - return restart_syscall(); + ret = sysfs_rtnl_lock(&dev->kobj, &attr->attr, netdev); + if (ret) + return ret; + ret = -EINVAL; if (netif_running(netdev)) { /* Synchronize carrier state with link watch, * see also rtnl_getlink(). @@ -245,8 +329,8 @@ static ssize_t carrier_show(struct device *dev, ret = sysfs_emit(buf, fmt_dec, !!netif_carrier_ok(netdev)); } - rtnl_unlock(); + rtnl_unlock(); return ret; } static DEVICE_ATTR_RW(carrier); @@ -258,14 +342,16 @@ static ssize_t speed_show(struct device *dev, int ret = -EINVAL; /* The check is also done in __ethtool_get_link_ksettings; this helps - * returning early without hitting the trylock/restart below. + * returning early without hitting the locking section below. */ if (!netdev->ethtool_ops->get_link_ksettings) return ret; - if (!rtnl_trylock()) - return restart_syscall(); + ret = sysfs_rtnl_lock(&dev->kobj, &attr->attr, netdev); + if (ret) + return ret; + ret = -EINVAL; if (netif_running(netdev)) { struct ethtool_link_ksettings cmd; @@ -284,14 +370,16 @@ static ssize_t duplex_show(struct device *dev, int ret = -EINVAL; /* The check is also done in __ethtool_get_link_ksettings; this helps - * returning early without hitting the trylock/restart below. + * returning early without hitting the locking section below. */ if (!netdev->ethtool_ops->get_link_ksettings) return ret; - if (!rtnl_trylock()) - return restart_syscall(); + ret = sysfs_rtnl_lock(&dev->kobj, &attr->attr, netdev); + if (ret) + return ret; + ret = -EINVAL; if (netif_running(netdev)) { struct ethtool_link_ksettings cmd; @@ -481,7 +569,7 @@ static ssize_t ifalias_store(struct device *dev, struct device_attribute *attr, struct net_device *netdev = to_net_dev(dev); struct net *net = dev_net(netdev); size_t count = len; - ssize_t ret = 0; + ssize_t ret; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; @@ -490,16 +578,15 @@ static ssize_t ifalias_store(struct device *dev, struct device_attribute *attr, if (len > 0 && buf[len - 1] == '\n') --count; - if (!rtnl_trylock()) - return restart_syscall(); + ret = sysfs_rtnl_lock(&dev->kobj, &attr->attr, netdev); + if (ret) + return ret; - if (dev_isalive(netdev)) { - ret = dev_set_alias(netdev, buf, count); - if (ret < 0) - goto err; - ret = len; - netdev_state_change(netdev); - } + ret = dev_set_alias(netdev, buf, count); + if (ret < 0) + goto err; + ret = len; + netdev_state_change(netdev); err: rtnl_unlock(); @@ -511,7 +598,7 @@ static ssize_t ifalias_show(struct device *dev, { const struct net_device *netdev = to_net_dev(dev); char tmp[IFALIASZ]; - ssize_t ret = 0; + ssize_t ret; ret = dev_get_alias(netdev, tmp, sizeof(tmp)); if (ret > 0) @@ -551,24 +638,23 @@ static ssize_t phys_port_id_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *netdev = to_net_dev(dev); - ssize_t ret = -EINVAL; + struct netdev_phys_item_id ppid; + ssize_t ret; /* The check is also done in dev_get_phys_port_id; this helps returning - * early without hitting the trylock/restart below. + * early without hitting the locking section below. */ if (!netdev->netdev_ops->ndo_get_phys_port_id) return -EOPNOTSUPP; - if (!rtnl_trylock()) - return restart_syscall(); + ret = sysfs_rtnl_lock(&dev->kobj, &attr->attr, netdev); + if (ret) + return ret; - if (dev_isalive(netdev)) { - struct netdev_phys_item_id ppid; + ret = dev_get_phys_port_id(netdev, &ppid); + if (!ret) + ret = sysfs_emit(buf, "%*phN\n", ppid.id_len, ppid.id); - ret = dev_get_phys_port_id(netdev, &ppid); - if (!ret) - ret = sysfs_emit(buf, "%*phN\n", ppid.id_len, ppid.id); - } rtnl_unlock(); return ret; @@ -579,25 +665,24 @@ static ssize_t phys_port_name_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *netdev = to_net_dev(dev); - ssize_t ret = -EINVAL; + char name[IFNAMSIZ]; + ssize_t ret; /* The checks are also done in dev_get_phys_port_name; this helps - * returning early without hitting the trylock/restart below. + * returning early without hitting the locking section below. */ if (!netdev->netdev_ops->ndo_get_phys_port_name && !netdev->devlink_port) return -EOPNOTSUPP; - if (!rtnl_trylock()) - return restart_syscall(); + ret = sysfs_rtnl_lock(&dev->kobj, &attr->attr, netdev); + if (ret) + return ret; - if (dev_isalive(netdev)) { - char name[IFNAMSIZ]; + ret = dev_get_phys_port_name(netdev, name, sizeof(name)); + if (!ret) + ret = sysfs_emit(buf, "%s\n", name); - ret = dev_get_phys_port_name(netdev, name, sizeof(name)); - if (!ret) - ret = sysfs_emit(buf, "%s\n", name); - } rtnl_unlock(); return ret; @@ -608,26 +693,25 @@ static ssize_t phys_switch_id_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *netdev = to_net_dev(dev); - ssize_t ret = -EINVAL; + struct netdev_phys_item_id ppid = { }; + ssize_t ret; /* The checks are also done in dev_get_phys_port_name; this helps - * returning early without hitting the trylock/restart below. This works + * returning early without hitting the locking section below. This works * because recurse is false when calling dev_get_port_parent_id. */ if (!netdev->netdev_ops->ndo_get_port_parent_id && !netdev->devlink_port) return -EOPNOTSUPP; - if (!rtnl_trylock()) - return restart_syscall(); + ret = sysfs_rtnl_lock(&dev->kobj, &attr->attr, netdev); + if (ret) + return ret; - if (dev_isalive(netdev)) { - struct netdev_phys_item_id ppid = { }; + ret = dev_get_port_parent_id(netdev, &ppid, false); + if (!ret) + ret = sysfs_emit(buf, "%*phN\n", ppid.id_len, ppid.id); - ret = dev_get_port_parent_id(netdev, &ppid, false); - if (!ret) - ret = sysfs_emit(buf, "%*phN\n", ppid.id_len, ppid.id); - } rtnl_unlock(); return ret; @@ -972,7 +1056,7 @@ static ssize_t show_rps_dev_flow_table_cnt(struct netdev_rx_queue *queue, rcu_read_lock(); flow_table = rcu_dereference(queue->rps_flow_table); if (flow_table) - val = (unsigned long)flow_table->mask + 1; + val = 1UL << flow_table->log; rcu_read_unlock(); return sysfs_emit(buf, "%lu\n", val); @@ -1025,7 +1109,7 @@ static ssize_t store_rps_dev_flow_table_cnt(struct netdev_rx_queue *queue, if (!table) return -ENOMEM; - table->mask = mask; + table->log = ilog2(mask) + 1; for (count = 0; count <= mask; count++) table->flows[count].cpu = RPS_NO_CPU; } else { @@ -1108,7 +1192,6 @@ static void rx_queue_get_ownership(const struct kobject *kobj, static const struct kobj_type rx_queue_ktype = { .sysfs_ops = &rx_queue_sysfs_ops, .release = rx_queue_release, - .default_groups = rx_queue_default_groups, .namespace = rx_queue_namespace, .get_ownership = rx_queue_get_ownership, }; @@ -1131,6 +1214,22 @@ static int rx_queue_add_kobject(struct net_device *dev, int index) struct kobject *kobj = &queue->kobj; int error = 0; + /* Rx queues are cleared in rx_queue_release to allow later + * re-registration. This is triggered when their kobj refcount is + * dropped. + * + * If a queue is removed while both a read (or write) operation and a + * the re-addition of the same queue are pending (waiting on rntl_lock) + * it might happen that the re-addition will execute before the read, + * making the initial removal to never happen (queue's kobj refcount + * won't drop enough because of the pending read). In such rare case, + * return to allow the removal operation to complete. + */ + if (unlikely(kobj->state_initialized)) { + netdev_warn_once(dev, "Cannot re-add rx queues before their removal completed"); + return -EAGAIN; + } + /* Kobject_put later will trigger rx_queue_release call which * decreases dev refcount: Take that reference here */ @@ -1142,20 +1241,27 @@ static int rx_queue_add_kobject(struct net_device *dev, int index) if (error) goto err; + queue->groups = rx_queue_default_groups; + error = sysfs_create_groups(kobj, queue->groups); + if (error) + goto err; + if (dev->sysfs_rx_queue_group) { error = sysfs_create_group(kobj, dev->sysfs_rx_queue_group); if (error) - goto err; + goto err_default_groups; } error = rx_queue_default_mask(dev, queue); if (error) - goto err; + goto err_default_groups; kobject_uevent(kobj, KOBJ_ADD); return error; +err_default_groups: + sysfs_remove_groups(kobj, queue->groups); err: kobject_put(kobj); return error; @@ -1200,12 +1306,14 @@ net_rx_queue_update_kobjects(struct net_device *dev, int old_num, int new_num) } while (--i >= new_num) { - struct kobject *kobj = &dev->_rx[i].kobj; + struct netdev_rx_queue *queue = &dev->_rx[i]; + struct kobject *kobj = &queue->kobj; if (!refcount_read(&dev_net(dev)->ns.count)) kobj->uevent_suppress = 1; if (dev->sysfs_rx_queue_group) sysfs_remove_group(kobj, dev->sysfs_rx_queue_group); + sysfs_remove_groups(kobj, queue->groups); kobject_put(kobj); } @@ -1244,9 +1352,11 @@ static int net_rx_queue_change_owner(struct net_device *dev, int num, */ struct netdev_queue_attribute { struct attribute attr; - ssize_t (*show)(struct netdev_queue *queue, char *buf); - ssize_t (*store)(struct netdev_queue *queue, - const char *buf, size_t len); + ssize_t (*show)(struct kobject *kobj, struct attribute *attr, + struct netdev_queue *queue, char *buf); + ssize_t (*store)(struct kobject *kobj, struct attribute *attr, + struct netdev_queue *queue, const char *buf, + size_t len); }; #define to_netdev_queue_attr(_attr) \ container_of(_attr, struct netdev_queue_attribute, attr) @@ -1263,7 +1373,7 @@ static ssize_t netdev_queue_attr_show(struct kobject *kobj, if (!attribute->show) return -EIO; - return attribute->show(queue, buf); + return attribute->show(kobj, attr, queue, buf); } static ssize_t netdev_queue_attr_store(struct kobject *kobj, @@ -1277,7 +1387,7 @@ static ssize_t netdev_queue_attr_store(struct kobject *kobj, if (!attribute->store) return -EIO; - return attribute->store(queue, buf, count); + return attribute->store(kobj, attr, queue, buf, count); } static const struct sysfs_ops netdev_queue_sysfs_ops = { @@ -1285,7 +1395,8 @@ static const struct sysfs_ops netdev_queue_sysfs_ops = { .store = netdev_queue_attr_store, }; -static ssize_t tx_timeout_show(struct netdev_queue *queue, char *buf) +static ssize_t tx_timeout_show(struct kobject *kobj, struct attribute *attr, + struct netdev_queue *queue, char *buf) { unsigned long trans_timeout = atomic_long_read(&queue->trans_timeout); @@ -1303,18 +1414,18 @@ static unsigned int get_netdev_queue_index(struct netdev_queue *queue) return i; } -static ssize_t traffic_class_show(struct netdev_queue *queue, - char *buf) +static ssize_t traffic_class_show(struct kobject *kobj, struct attribute *attr, + struct netdev_queue *queue, char *buf) { struct net_device *dev = queue->dev; - int num_tc, tc; - int index; + int num_tc, tc, index, ret; if (!netif_is_multiqueue(dev)) return -ENOENT; - if (!rtnl_trylock()) - return restart_syscall(); + ret = sysfs_rtnl_lock(kobj, attr, queue->dev); + if (ret) + return ret; index = get_netdev_queue_index(queue); @@ -1341,24 +1452,25 @@ static ssize_t traffic_class_show(struct netdev_queue *queue, } #ifdef CONFIG_XPS -static ssize_t tx_maxrate_show(struct netdev_queue *queue, - char *buf) +static ssize_t tx_maxrate_show(struct kobject *kobj, struct attribute *attr, + struct netdev_queue *queue, char *buf) { return sysfs_emit(buf, "%lu\n", queue->tx_maxrate); } -static ssize_t tx_maxrate_store(struct netdev_queue *queue, - const char *buf, size_t len) +static ssize_t tx_maxrate_store(struct kobject *kobj, struct attribute *attr, + struct netdev_queue *queue, const char *buf, + size_t len) { - struct net_device *dev = queue->dev; int err, index = get_netdev_queue_index(queue); + struct net_device *dev = queue->dev; u32 rate = 0; if (!capable(CAP_NET_ADMIN)) return -EPERM; /* The check is also done later; this helps returning early without - * hitting the trylock/restart below. + * hitting the locking section below. */ if (!dev->netdev_ops->ndo_set_tx_maxrate) return -EOPNOTSUPP; @@ -1367,18 +1479,23 @@ static ssize_t tx_maxrate_store(struct netdev_queue *queue, if (err < 0) return err; - if (!rtnl_trylock()) - return restart_syscall(); + err = sysfs_rtnl_lock(kobj, attr, dev); + if (err) + return err; err = -EOPNOTSUPP; + netdev_lock_ops(dev); if (dev->netdev_ops->ndo_set_tx_maxrate) err = dev->netdev_ops->ndo_set_tx_maxrate(dev, index, rate); + netdev_unlock_ops(dev); - rtnl_unlock(); if (!err) { queue->tx_maxrate = rate; + rtnl_unlock(); return len; } + + rtnl_unlock(); return err; } @@ -1422,16 +1539,17 @@ static ssize_t bql_set(const char *buf, const size_t count, return count; } -static ssize_t bql_show_hold_time(struct netdev_queue *queue, - char *buf) +static ssize_t bql_show_hold_time(struct kobject *kobj, struct attribute *attr, + struct netdev_queue *queue, char *buf) { struct dql *dql = &queue->dql; return sysfs_emit(buf, "%u\n", jiffies_to_msecs(dql->slack_hold_time)); } -static ssize_t bql_set_hold_time(struct netdev_queue *queue, - const char *buf, size_t len) +static ssize_t bql_set_hold_time(struct kobject *kobj, struct attribute *attr, + struct netdev_queue *queue, const char *buf, + size_t len) { struct dql *dql = &queue->dql; unsigned int value; @@ -1450,15 +1568,17 @@ static struct netdev_queue_attribute bql_hold_time_attribute __ro_after_init = __ATTR(hold_time, 0644, bql_show_hold_time, bql_set_hold_time); -static ssize_t bql_show_stall_thrs(struct netdev_queue *queue, char *buf) +static ssize_t bql_show_stall_thrs(struct kobject *kobj, struct attribute *attr, + struct netdev_queue *queue, char *buf) { struct dql *dql = &queue->dql; return sysfs_emit(buf, "%u\n", jiffies_to_msecs(dql->stall_thrs)); } -static ssize_t bql_set_stall_thrs(struct netdev_queue *queue, - const char *buf, size_t len) +static ssize_t bql_set_stall_thrs(struct kobject *kobj, struct attribute *attr, + struct netdev_queue *queue, const char *buf, + size_t len) { struct dql *dql = &queue->dql; unsigned int value; @@ -1484,13 +1604,15 @@ static ssize_t bql_set_stall_thrs(struct netdev_queue *queue, static struct netdev_queue_attribute bql_stall_thrs_attribute __ro_after_init = __ATTR(stall_thrs, 0644, bql_show_stall_thrs, bql_set_stall_thrs); -static ssize_t bql_show_stall_max(struct netdev_queue *queue, char *buf) +static ssize_t bql_show_stall_max(struct kobject *kobj, struct attribute *attr, + struct netdev_queue *queue, char *buf) { return sysfs_emit(buf, "%u\n", READ_ONCE(queue->dql.stall_max)); } -static ssize_t bql_set_stall_max(struct netdev_queue *queue, - const char *buf, size_t len) +static ssize_t bql_set_stall_max(struct kobject *kobj, struct attribute *attr, + struct netdev_queue *queue, const char *buf, + size_t len) { WRITE_ONCE(queue->dql.stall_max, 0); return len; @@ -1499,7 +1621,8 @@ static ssize_t bql_set_stall_max(struct netdev_queue *queue, static struct netdev_queue_attribute bql_stall_max_attribute __ro_after_init = __ATTR(stall_max, 0644, bql_show_stall_max, bql_set_stall_max); -static ssize_t bql_show_stall_cnt(struct netdev_queue *queue, char *buf) +static ssize_t bql_show_stall_cnt(struct kobject *kobj, struct attribute *attr, + struct netdev_queue *queue, char *buf) { struct dql *dql = &queue->dql; @@ -1509,8 +1632,8 @@ static ssize_t bql_show_stall_cnt(struct netdev_queue *queue, char *buf) static struct netdev_queue_attribute bql_stall_cnt_attribute __ro_after_init = __ATTR(stall_cnt, 0444, bql_show_stall_cnt, NULL); -static ssize_t bql_show_inflight(struct netdev_queue *queue, - char *buf) +static ssize_t bql_show_inflight(struct kobject *kobj, struct attribute *attr, + struct netdev_queue *queue, char *buf) { struct dql *dql = &queue->dql; @@ -1521,13 +1644,16 @@ static struct netdev_queue_attribute bql_inflight_attribute __ro_after_init = __ATTR(inflight, 0444, bql_show_inflight, NULL); #define BQL_ATTR(NAME, FIELD) \ -static ssize_t bql_show_ ## NAME(struct netdev_queue *queue, \ - char *buf) \ +static ssize_t bql_show_ ## NAME(struct kobject *kobj, \ + struct attribute *attr, \ + struct netdev_queue *queue, char *buf) \ { \ return bql_show(buf, queue->dql.FIELD); \ } \ \ -static ssize_t bql_set_ ## NAME(struct netdev_queue *queue, \ +static ssize_t bql_set_ ## NAME(struct kobject *kobj, \ + struct attribute *attr, \ + struct netdev_queue *queue, \ const char *buf, size_t len) \ { \ return bql_set(buf, len, &queue->dql.FIELD); \ @@ -1613,19 +1739,21 @@ out_no_maps: return len < PAGE_SIZE ? len : -EINVAL; } -static ssize_t xps_cpus_show(struct netdev_queue *queue, char *buf) +static ssize_t xps_cpus_show(struct kobject *kobj, struct attribute *attr, + struct netdev_queue *queue, char *buf) { struct net_device *dev = queue->dev; unsigned int index; - int len, tc; + int len, tc, ret; if (!netif_is_multiqueue(dev)) return -ENOENT; index = get_netdev_queue_index(queue); - if (!rtnl_trylock()) - return restart_syscall(); + ret = sysfs_rtnl_lock(kobj, attr, queue->dev); + if (ret) + return ret; /* If queue belongs to subordinate dev use its map */ dev = netdev_get_tx_queue(dev, index)->sb_dev ? : dev; @@ -1636,18 +1764,21 @@ static ssize_t xps_cpus_show(struct netdev_queue *queue, char *buf) return -EINVAL; } - /* Make sure the subordinate device can't be freed */ - get_device(&dev->dev); + /* Increase the net device refcnt to make sure it won't be freed while + * xps_queue_show is running. + */ + dev_hold(dev); rtnl_unlock(); len = xps_queue_show(dev, index, tc, buf, XPS_CPUS); - put_device(&dev->dev); + dev_put(dev); return len; } -static ssize_t xps_cpus_store(struct netdev_queue *queue, - const char *buf, size_t len) +static ssize_t xps_cpus_store(struct kobject *kobj, struct attribute *attr, + struct netdev_queue *queue, const char *buf, + size_t len) { struct net_device *dev = queue->dev; unsigned int index; @@ -1671,9 +1802,10 @@ static ssize_t xps_cpus_store(struct netdev_queue *queue, return err; } - if (!rtnl_trylock()) { + err = sysfs_rtnl_lock(kobj, attr, dev); + if (err) { free_cpumask_var(mask); - return restart_syscall(); + return err; } err = netif_set_xps_queue(dev, mask, index); @@ -1687,26 +1819,34 @@ static ssize_t xps_cpus_store(struct netdev_queue *queue, static struct netdev_queue_attribute xps_cpus_attribute __ro_after_init = __ATTR_RW(xps_cpus); -static ssize_t xps_rxqs_show(struct netdev_queue *queue, char *buf) +static ssize_t xps_rxqs_show(struct kobject *kobj, struct attribute *attr, + struct netdev_queue *queue, char *buf) { struct net_device *dev = queue->dev; unsigned int index; - int tc; + int tc, ret; index = get_netdev_queue_index(queue); - if (!rtnl_trylock()) - return restart_syscall(); + ret = sysfs_rtnl_lock(kobj, attr, dev); + if (ret) + return ret; tc = netdev_txq_to_tc(dev, index); + + /* Increase the net device refcnt to make sure it won't be freed while + * xps_queue_show is running. + */ + dev_hold(dev); rtnl_unlock(); - if (tc < 0) - return -EINVAL; - return xps_queue_show(dev, index, tc, buf, XPS_RXQS); + ret = tc >= 0 ? xps_queue_show(dev, index, tc, buf, XPS_RXQS) : -EINVAL; + dev_put(dev); + return ret; } -static ssize_t xps_rxqs_store(struct netdev_queue *queue, const char *buf, +static ssize_t xps_rxqs_store(struct kobject *kobj, struct attribute *attr, + struct netdev_queue *queue, const char *buf, size_t len) { struct net_device *dev = queue->dev; @@ -1730,9 +1870,10 @@ static ssize_t xps_rxqs_store(struct netdev_queue *queue, const char *buf, return err; } - if (!rtnl_trylock()) { + err = sysfs_rtnl_lock(kobj, attr, dev); + if (err) { bitmap_free(mask); - return restart_syscall(); + return err; } cpus_read_lock(); @@ -1792,7 +1933,6 @@ static void netdev_queue_get_ownership(const struct kobject *kobj, static const struct kobj_type netdev_queue_ktype = { .sysfs_ops = &netdev_queue_sysfs_ops, .release = netdev_queue_release, - .default_groups = netdev_queue_default_groups, .namespace = netdev_queue_namespace, .get_ownership = netdev_queue_get_ownership, }; @@ -1811,6 +1951,22 @@ static int netdev_queue_add_kobject(struct net_device *dev, int index) struct kobject *kobj = &queue->kobj; int error = 0; + /* Tx queues are cleared in netdev_queue_release to allow later + * re-registration. This is triggered when their kobj refcount is + * dropped. + * + * If a queue is removed while both a read (or write) operation and a + * the re-addition of the same queue are pending (waiting on rntl_lock) + * it might happen that the re-addition will execute before the read, + * making the initial removal to never happen (queue's kobj refcount + * won't drop enough because of the pending read). In such rare case, + * return to allow the removal operation to complete. + */ + if (unlikely(kobj->state_initialized)) { + netdev_warn_once(dev, "Cannot re-add tx queues before their removal completed"); + return -EAGAIN; + } + /* Kobject_put later will trigger netdev_queue_release call * which decreases dev refcount: Take that reference here */ @@ -1822,15 +1978,22 @@ static int netdev_queue_add_kobject(struct net_device *dev, int index) if (error) goto err; + queue->groups = netdev_queue_default_groups; + error = sysfs_create_groups(kobj, queue->groups); + if (error) + goto err; + if (netdev_uses_bql(dev)) { error = sysfs_create_group(kobj, &dql_group); if (error) - goto err; + goto err_default_groups; } kobject_uevent(kobj, KOBJ_ADD); return 0; +err_default_groups: + sysfs_remove_groups(kobj, queue->groups); err: kobject_put(kobj); return error; @@ -1885,6 +2048,7 @@ netdev_queue_update_kobjects(struct net_device *dev, int old_num, int new_num) if (netdev_uses_bql(dev)) sysfs_remove_group(&queue->kobj, &dql_group); + sysfs_remove_groups(&queue->kobj, queue->groups); kobject_put(&queue->kobj); } @@ -1984,8 +2148,10 @@ static void remove_queue_kobjects(struct net_device *dev) net_rx_queue_update_kobjects(dev, real_rx, 0); netdev_queue_update_kobjects(dev, real_tx, 0); + netdev_lock_ops(dev); dev->real_num_rx_queues = 0; dev->real_num_tx_queues = 0; + netdev_unlock_ops(dev); #ifdef CONFIG_SYSFS kset_unregister(dev->queues_kset); #endif diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index cb39a12b2f82..b0dfdf791ece 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -340,6 +340,8 @@ static __net_init void preinit_net(struct net *net, struct user_namespace *user_ lock_set_cmp_fn(&net->rtnl_mutex, rtnl_net_lock_cmp_fn, NULL); #endif + INIT_LIST_HEAD(&net->ptype_all); + INIT_LIST_HEAD(&net->ptype_specific); preinit_net_sysctl(net); } @@ -464,7 +466,7 @@ static void net_complete_free(void) } -static void net_free(struct net *net) +void net_passive_dec(struct net *net) { if (refcount_dec_and_test(&net->passive)) { kfree(rcu_access_pointer(net->gen)); @@ -482,7 +484,7 @@ void net_drop_ns(void *p) struct net *net = (struct net *)p; if (net) - net_free(net); + net_passive_dec(net); } struct net *copy_net_ns(unsigned long flags, @@ -523,7 +525,7 @@ put_userns: key_remove_domain(net->key_domain); #endif put_user_ns(user_ns); - net_free(net); + net_passive_dec(net); dec_ucounts: dec_net_namespaces(ucounts); return ERR_PTR(rv); @@ -672,7 +674,7 @@ static void cleanup_net(struct work_struct *work) key_remove_domain(net->key_domain); #endif put_user_ns(net->user_ns); - net_free(net); + net_passive_dec(net); } cleanup_net_task = NULL; } diff --git a/net/core/netdev-genl-gen.c b/net/core/netdev-genl-gen.c index 996ac6a449eb..739f7b6506a6 100644 --- a/net/core/netdev-genl-gen.c +++ b/net/core/netdev-genl-gen.c @@ -9,7 +9,7 @@ #include "netdev-genl-gen.h" #include <uapi/linux/netdev.h> -#include <linux/list.h> +#include <net/netdev_netlink.h> /* Integer value ranges */ static const struct netlink_range_validation netdev_a_page_pool_id_range = { @@ -217,7 +217,7 @@ struct genl_family netdev_nl_family __ro_after_init = { .n_split_ops = ARRAY_SIZE(netdev_nl_ops), .mcgrps = netdev_nl_mcgrps, .n_mcgrps = ARRAY_SIZE(netdev_nl_mcgrps), - .sock_priv_size = sizeof(struct list_head), + .sock_priv_size = sizeof(struct netdev_nl_sock), .sock_priv_init = __netdev_nl_sock_priv_init, .sock_priv_destroy = __netdev_nl_sock_priv_destroy, }; diff --git a/net/core/netdev-genl-gen.h b/net/core/netdev-genl-gen.h index e09dd7539ff2..17d39fd64c94 100644 --- a/net/core/netdev-genl-gen.h +++ b/net/core/netdev-genl-gen.h @@ -10,7 +10,7 @@ #include <net/genetlink.h> #include <uapi/linux/netdev.h> -#include <linux/list.h> +#include <net/netdev_netlink.h> /* Common nested types */ extern const struct nla_policy netdev_page_pool_info_nl_policy[NETDEV_A_PAGE_POOL_IFINDEX + 1]; @@ -42,7 +42,7 @@ enum { extern struct genl_family netdev_nl_family; -void netdev_nl_sock_priv_init(struct list_head *priv); -void netdev_nl_sock_priv_destroy(struct list_head *priv); +void netdev_nl_sock_priv_init(struct netdev_nl_sock *priv); +void netdev_nl_sock_priv_destroy(struct netdev_nl_sock *priv); #endif /* _LINUX_NETDEV_GEN_H */ diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c index 715f85c6b62e..5d7af50fe702 100644 --- a/net/core/netdev-genl.c +++ b/net/core/netdev-genl.c @@ -10,6 +10,7 @@ #include <net/sock.h> #include <net/xdp.h> #include <net/xdp_sock.h> +#include <net/page_pool/memory_provider.h> #include "dev.h" #include "devmem.h" @@ -52,6 +53,8 @@ XDP_METADATA_KFUNC_xxx xsk_features |= NETDEV_XSK_FLAGS_TX_TIMESTAMP; if (netdev->xsk_tx_metadata_ops->tmo_request_checksum) xsk_features |= NETDEV_XSK_FLAGS_TX_CHECKSUM; + if (netdev->xsk_tx_metadata_ops->tmo_request_launch_time) + xsk_features |= NETDEV_XSK_FLAGS_TX_LAUNCH_TIME_FIFO; } if (nla_put_u32(rsp, NETDEV_A_DEV_IFINDEX, netdev->ifindex) || @@ -266,7 +269,7 @@ netdev_nl_napi_dump_one(struct net_device *netdev, struct sk_buff *rsp, prev_id = UINT_MAX; list_for_each_entry(napi, &netdev->napi_list, dev_list) { - if (napi->napi_id < MIN_NAPI_ID) + if (!napi_id_valid(napi->napi_id)) continue; /* Dump continuation below depends on the list being sorted */ @@ -364,11 +367,18 @@ int netdev_nl_napi_set_doit(struct sk_buff *skb, struct genl_info *info) return err; } +static int nla_put_napi_id(struct sk_buff *skb, const struct napi_struct *napi) +{ + if (napi && napi_id_valid(napi->napi_id)) + return nla_put_u32(skb, NETDEV_A_QUEUE_NAPI_ID, napi->napi_id); + return 0; +} + 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 net_devmem_dmabuf_binding *binding; + struct pp_memory_provider_params *params; struct netdev_rx_queue *rxq; struct netdev_queue *txq; void *hdr; @@ -385,21 +395,30 @@ netdev_nl_queue_fill_one(struct sk_buff *rsp, struct net_device *netdev, 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)) + if (nla_put_napi_id(rsp, rxq->napi)) goto nla_put_failure; - binding = rxq->mp_params.mp_priv; - if (binding && - nla_put_u32(rsp, NETDEV_A_QUEUE_DMABUF, binding->id)) + params = &rxq->mp_params; + if (params->mp_ops && + params->mp_ops->nl_fill(params->mp_priv, rsp, rxq)) goto nla_put_failure; +#ifdef CONFIG_XDP_SOCKETS + if (rxq->pool) + if (nla_put_empty_nest(rsp, NETDEV_A_QUEUE_XSK)) + goto nla_put_failure; +#endif 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)) + if (nla_put_napi_id(rsp, txq->napi)) goto nla_put_failure; +#ifdef CONFIG_XDP_SOCKETS + if (txq->pool) + if (nla_put_empty_nest(rsp, NETDEV_A_QUEUE_XSK)) + goto nla_put_failure; +#endif + break; } genlmsg_end(rsp, hdr); @@ -576,6 +595,7 @@ netdev_nl_stats_write_rx(struct sk_buff *rsp, struct netdev_queue_stats_rx *rx) netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_ALLOC_FAIL, rx->alloc_fail) || netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_HW_DROPS, rx->hw_drops) || netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_HW_DROP_OVERRUNS, rx->hw_drop_overruns) || + netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_CSUM_COMPLETE, rx->csum_complete) || netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_CSUM_UNNECESSARY, rx->csum_unnecessary) || netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_CSUM_NONE, rx->csum_none) || netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_CSUM_BAD, rx->csum_bad) || @@ -809,8 +829,8 @@ int netdev_nl_bind_rx_doit(struct sk_buff *skb, struct genl_info *info) { struct nlattr *tb[ARRAY_SIZE(netdev_queue_id_nl_policy)]; struct net_devmem_dmabuf_binding *binding; - struct list_head *sock_binding_list; u32 ifindex, dmabuf_fd, rxq_idx; + struct netdev_nl_sock *priv; struct net_device *netdev; struct sk_buff *rsp; struct nlattr *attr; @@ -825,10 +845,9 @@ int netdev_nl_bind_rx_doit(struct sk_buff *skb, struct genl_info *info) ifindex = nla_get_u32(info->attrs[NETDEV_A_DEV_IFINDEX]); dmabuf_fd = nla_get_u32(info->attrs[NETDEV_A_DMABUF_FD]); - sock_binding_list = genl_sk_priv_get(&netdev_nl_family, - NETLINK_CB(skb).sk); - if (IS_ERR(sock_binding_list)) - return PTR_ERR(sock_binding_list); + priv = genl_sk_priv_get(&netdev_nl_family, NETLINK_CB(skb).sk); + if (IS_ERR(priv)) + return PTR_ERR(priv); rsp = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!rsp) @@ -840,17 +859,18 @@ int netdev_nl_bind_rx_doit(struct sk_buff *skb, struct genl_info *info) goto err_genlmsg_free; } - rtnl_lock(); + mutex_lock(&priv->lock); - netdev = __dev_get_by_index(genl_info_net(info), ifindex); + netdev = netdev_get_by_index_lock(genl_info_net(info), ifindex); if (!netdev || !netif_device_present(netdev)) { err = -ENODEV; - goto err_unlock; + goto err_unlock_sock; } - if (dev_xdp_prog_count(netdev)) { - NL_SET_ERR_MSG(info->extack, "unable to bind dmabuf to device with XDP program attached"); - err = -EEXIST; + if (!netdev_need_ops_lock(netdev)) { + err = -EOPNOTSUPP; + NL_SET_BAD_ATTR(info->extack, + info->attrs[NETDEV_A_DEV_IFINDEX]); goto err_unlock; } @@ -889,7 +909,7 @@ int netdev_nl_bind_rx_doit(struct sk_buff *skb, struct genl_info *info) goto err_unbind; } - list_add(&binding->list, sock_binding_list); + list_add(&binding->list, &priv->bindings); nla_put_u32(rsp, NETDEV_A_DMABUF_ID, binding->id); genlmsg_end(rsp, hdr); @@ -898,34 +918,43 @@ int netdev_nl_bind_rx_doit(struct sk_buff *skb, struct genl_info *info) if (err) goto err_unbind; - rtnl_unlock(); + netdev_unlock(netdev); + + mutex_unlock(&priv->lock); return 0; err_unbind: net_devmem_unbind_dmabuf(binding); err_unlock: - rtnl_unlock(); + netdev_unlock(netdev); +err_unlock_sock: + mutex_unlock(&priv->lock); err_genlmsg_free: nlmsg_free(rsp); return err; } -void netdev_nl_sock_priv_init(struct list_head *priv) +void netdev_nl_sock_priv_init(struct netdev_nl_sock *priv) { - INIT_LIST_HEAD(priv); + INIT_LIST_HEAD(&priv->bindings); + mutex_init(&priv->lock); } -void netdev_nl_sock_priv_destroy(struct list_head *priv) +void netdev_nl_sock_priv_destroy(struct netdev_nl_sock *priv) { struct net_devmem_dmabuf_binding *binding; struct net_devmem_dmabuf_binding *temp; + struct net_device *dev; - list_for_each_entry_safe(binding, temp, priv, list) { - rtnl_lock(); + mutex_lock(&priv->lock); + list_for_each_entry_safe(binding, temp, &priv->bindings, list) { + dev = binding->dev; + netdev_lock(dev); net_devmem_unbind_dmabuf(binding); - rtnl_unlock(); + netdev_unlock(dev); } + mutex_unlock(&priv->lock); } static int netdev_genl_netdevice_event(struct notifier_block *nb, diff --git a/net/core/netdev_rx_queue.c b/net/core/netdev_rx_queue.c index db82786fa0c4..d126f10197bf 100644 --- a/net/core/netdev_rx_queue.c +++ b/net/core/netdev_rx_queue.c @@ -1,36 +1,38 @@ // SPDX-License-Identifier: GPL-2.0-or-later +#include <linux/ethtool_netlink.h> #include <linux/netdevice.h> +#include <net/netdev_lock.h> #include <net/netdev_queues.h> #include <net/netdev_rx_queue.h> +#include <net/page_pool/memory_provider.h> #include "page_pool_priv.h" int netdev_rx_queue_restart(struct net_device *dev, unsigned int rxq_idx) { struct netdev_rx_queue *rxq = __netif_get_rx_queue(dev, rxq_idx); + const struct netdev_queue_mgmt_ops *qops = dev->queue_mgmt_ops; void *new_mem, *old_mem; int err; - if (!dev->queue_mgmt_ops || !dev->queue_mgmt_ops->ndo_queue_stop || - !dev->queue_mgmt_ops->ndo_queue_mem_free || - !dev->queue_mgmt_ops->ndo_queue_mem_alloc || - !dev->queue_mgmt_ops->ndo_queue_start) + if (!qops || !qops->ndo_queue_stop || !qops->ndo_queue_mem_free || + !qops->ndo_queue_mem_alloc || !qops->ndo_queue_start) return -EOPNOTSUPP; - ASSERT_RTNL(); + netdev_assert_locked(dev); - new_mem = kvzalloc(dev->queue_mgmt_ops->ndo_queue_mem_size, GFP_KERNEL); + new_mem = kvzalloc(qops->ndo_queue_mem_size, GFP_KERNEL); if (!new_mem) return -ENOMEM; - old_mem = kvzalloc(dev->queue_mgmt_ops->ndo_queue_mem_size, GFP_KERNEL); + old_mem = kvzalloc(qops->ndo_queue_mem_size, GFP_KERNEL); if (!old_mem) { err = -ENOMEM; goto err_free_new_mem; } - err = dev->queue_mgmt_ops->ndo_queue_mem_alloc(dev, new_mem, rxq_idx); + err = qops->ndo_queue_mem_alloc(dev, new_mem, rxq_idx); if (err) goto err_free_old_mem; @@ -38,15 +40,19 @@ int netdev_rx_queue_restart(struct net_device *dev, unsigned int rxq_idx) if (err) goto err_free_new_queue_mem; - err = dev->queue_mgmt_ops->ndo_queue_stop(dev, old_mem, rxq_idx); - if (err) - goto err_free_new_queue_mem; + if (netif_running(dev)) { + err = qops->ndo_queue_stop(dev, old_mem, rxq_idx); + if (err) + goto err_free_new_queue_mem; - err = dev->queue_mgmt_ops->ndo_queue_start(dev, new_mem, rxq_idx); - if (err) - goto err_start_queue; + err = qops->ndo_queue_start(dev, new_mem, rxq_idx); + if (err) + goto err_start_queue; + } else { + swap(new_mem, old_mem); + } - dev->queue_mgmt_ops->ndo_queue_mem_free(dev, old_mem); + qops->ndo_queue_mem_free(dev, old_mem); kvfree(old_mem); kvfree(new_mem); @@ -61,15 +67,15 @@ err_start_queue: * WARN if we fail to recover the old rx queue, and at least free * old_mem so we don't also leak that. */ - if (dev->queue_mgmt_ops->ndo_queue_start(dev, old_mem, rxq_idx)) { + if (qops->ndo_queue_start(dev, old_mem, rxq_idx)) { WARN(1, "Failed to restart old queue in error path. RX queue %d may be unhealthy.", rxq_idx); - dev->queue_mgmt_ops->ndo_queue_mem_free(dev, old_mem); + qops->ndo_queue_mem_free(dev, old_mem); } err_free_new_queue_mem: - dev->queue_mgmt_ops->ndo_queue_mem_free(dev, new_mem); + qops->ndo_queue_mem_free(dev, new_mem); err_free_old_mem: kvfree(old_mem); @@ -80,3 +86,102 @@ err_free_new_mem: return err; } EXPORT_SYMBOL_NS_GPL(netdev_rx_queue_restart, "NETDEV_INTERNAL"); + +int __net_mp_open_rxq(struct net_device *dev, unsigned int rxq_idx, + const struct pp_memory_provider_params *p, + struct netlink_ext_ack *extack) +{ + struct netdev_rx_queue *rxq; + int ret; + + if (!netdev_need_ops_lock(dev)) + return -EOPNOTSUPP; + + if (rxq_idx >= dev->real_num_rx_queues) + return -EINVAL; + rxq_idx = array_index_nospec(rxq_idx, dev->real_num_rx_queues); + + if (rxq_idx >= dev->real_num_rx_queues) { + NL_SET_ERR_MSG(extack, "rx queue index out of range"); + return -ERANGE; + } + if (dev->cfg->hds_config != ETHTOOL_TCP_DATA_SPLIT_ENABLED) { + NL_SET_ERR_MSG(extack, "tcp-data-split is disabled"); + return -EINVAL; + } + if (dev->cfg->hds_thresh) { + NL_SET_ERR_MSG(extack, "hds-thresh is not zero"); + return -EINVAL; + } + if (dev_xdp_prog_count(dev)) { + NL_SET_ERR_MSG(extack, "unable to custom memory provider to device with XDP program attached"); + return -EEXIST; + } + + rxq = __netif_get_rx_queue(dev, rxq_idx); + if (rxq->mp_params.mp_ops) { + NL_SET_ERR_MSG(extack, "designated queue already memory provider bound"); + return -EEXIST; + } +#ifdef CONFIG_XDP_SOCKETS + if (rxq->pool) { + NL_SET_ERR_MSG(extack, "designated queue already in use by AF_XDP"); + return -EBUSY; + } +#endif + + rxq->mp_params = *p; + ret = netdev_rx_queue_restart(dev, rxq_idx); + if (ret) { + rxq->mp_params.mp_ops = NULL; + rxq->mp_params.mp_priv = NULL; + } + return ret; +} + +int net_mp_open_rxq(struct net_device *dev, unsigned int rxq_idx, + struct pp_memory_provider_params *p) +{ + int ret; + + netdev_lock(dev); + ret = __net_mp_open_rxq(dev, rxq_idx, p, NULL); + netdev_unlock(dev); + return ret; +} + +void __net_mp_close_rxq(struct net_device *dev, unsigned int ifq_idx, + const struct pp_memory_provider_params *old_p) +{ + struct netdev_rx_queue *rxq; + int err; + + if (WARN_ON_ONCE(ifq_idx >= dev->real_num_rx_queues)) + return; + + rxq = __netif_get_rx_queue(dev, ifq_idx); + + /* Callers holding a netdev ref may get here after we already + * went thru shutdown via dev_memory_provider_uninstall(). + */ + if (dev->reg_state > NETREG_REGISTERED && + !rxq->mp_params.mp_ops) + return; + + if (WARN_ON_ONCE(rxq->mp_params.mp_ops != old_p->mp_ops || + rxq->mp_params.mp_priv != old_p->mp_priv)) + return; + + rxq->mp_params.mp_ops = NULL; + rxq->mp_params.mp_priv = NULL; + err = netdev_rx_queue_restart(dev, ifq_idx); + WARN_ON(err && err != -ENETDOWN); +} + +void net_mp_close_rxq(struct net_device *dev, unsigned ifq_idx, + struct pp_memory_provider_params *old_p) +{ + netdev_lock(dev); + __net_mp_close_rxq(dev, ifq_idx, old_p); + netdev_unlock(dev); +} diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 62b4041aae1a..4ddb7490df4b 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -284,12 +284,13 @@ static struct sk_buff *find_skb(struct netpoll *np, int len, int reserve) struct sk_buff *skb; zap_completion_queue(); - refill_skbs(np); repeat: skb = alloc_skb(len, GFP_ATOMIC); - if (!skb) + if (!skb) { skb = skb_dequeue(&np->skb_pool); + schedule_work(&np->refill_wq); + } if (!skb) { if (++count < 10) { @@ -319,6 +320,7 @@ static int netpoll_owner_active(struct net_device *dev) static netdev_tx_t __netpoll_send_skb(struct netpoll *np, struct sk_buff *skb) { netdev_tx_t status = NETDEV_TX_BUSY; + netdev_tx_t ret = NET_XMIT_DROP; struct net_device *dev; unsigned long tries; /* It is up to the caller to keep npinfo alive. */ @@ -327,11 +329,12 @@ static netdev_tx_t __netpoll_send_skb(struct netpoll *np, struct sk_buff *skb) lockdep_assert_irqs_disabled(); dev = np->dev; + rcu_read_lock(); npinfo = rcu_dereference_bh(dev->npinfo); if (!npinfo || !netif_running(dev) || !netif_device_present(dev)) { dev_kfree_skb_irq(skb); - return NET_XMIT_DROP; + goto out; } /* don't get messages out of order, and no recursion */ @@ -370,7 +373,10 @@ static netdev_tx_t __netpoll_send_skb(struct netpoll *np, struct sk_buff *skb) skb_queue_tail(&npinfo->txq, skb); schedule_delayed_work(&npinfo->tx_work,0); } - return NETDEV_TX_OK; + ret = NETDEV_TX_OK; +out: + rcu_read_unlock(); + return ret; } netdev_tx_t netpoll_send_skb(struct netpoll *np, struct sk_buff *skb) @@ -427,7 +433,6 @@ int netpoll_send_udp(struct netpoll *np, const char *msg, int len) udph->len = htons(udp_len); if (np->ipv6) { - udph->check = 0; udph->check = csum_ipv6_magic(&np->local_ip.in6, &np->remote_ip.in6, udp_len, IPPROTO_UDP, @@ -501,7 +506,8 @@ void netpoll_print_options(struct netpoll *np) np_info(np, "local IPv6 address %pI6c\n", &np->local_ip.in6); else np_info(np, "local IPv4 address %pI4\n", &np->local_ip.ip); - np_info(np, "interface '%s'\n", np->dev_name); + np_info(np, "interface name '%s'\n", np->dev_name); + np_info(np, "local ethernet address '%pM'\n", np->dev_mac); np_info(np, "remote port %d\n", np->remote_port); if (np->ipv6) np_info(np, "remote IPv6 address %pI6c\n", &np->remote_ip.in6); @@ -535,6 +541,7 @@ static void skb_pool_flush(struct netpoll *np) { struct sk_buff_head *skb_pool; + cancel_work_sync(&np->refill_wq); skb_pool = &np->skb_pool; skb_queue_purge_reason(skb_pool, SKB_CONSUMED); } @@ -570,11 +577,18 @@ int netpoll_parse_options(struct netpoll *np, char *opt) cur++; if (*cur != ',') { - /* parse out dev name */ + /* parse out dev_name or dev_mac */ if ((delim = strchr(cur, ',')) == NULL) goto parse_failed; *delim = 0; - strscpy(np->dev_name, cur, sizeof(np->dev_name)); + + np->dev_name[0] = '\0'; + eth_broadcast_addr(np->dev_mac); + if (!strchr(cur, ':')) + strscpy(np->dev_name, cur, sizeof(np->dev_name)); + else if (!mac_pton(cur, np->dev_mac)) + goto parse_failed; + cur = delim; } cur++; @@ -621,6 +635,14 @@ int netpoll_parse_options(struct netpoll *np, char *opt) } EXPORT_SYMBOL(netpoll_parse_options); +static void refill_skbs_work_handler(struct work_struct *work) +{ + struct netpoll *np = + container_of(work, struct netpoll, refill_wq); + + refill_skbs(np); +} + int __netpoll_setup(struct netpoll *np, struct net_device *ndev) { struct netpoll_info *npinfo; @@ -666,6 +688,7 @@ int __netpoll_setup(struct netpoll *np, struct net_device *ndev) /* fill up the skb queue */ refill_skbs(np); + INIT_WORK(&np->refill_wq, refill_skbs_work_handler); /* last thing to do is link it to the net device structure */ rcu_assign_pointer(ndev->npinfo, npinfo); @@ -679,27 +702,45 @@ out: } EXPORT_SYMBOL_GPL(__netpoll_setup); +/* + * Returns a pointer to a string representation of the identifier used + * to select the egress interface for the given netpoll instance. buf + * must be a buffer of length at least MAC_ADDR_STR_LEN + 1. + */ +static char *egress_dev(struct netpoll *np, char *buf) +{ + if (np->dev_name[0]) + return np->dev_name; + + snprintf(buf, MAC_ADDR_STR_LEN, "%pM", np->dev_mac); + return buf; +} + int netpoll_setup(struct netpoll *np) { + struct net *net = current->nsproxy->net_ns; + char buf[MAC_ADDR_STR_LEN + 1]; struct net_device *ndev = NULL; bool ip_overwritten = false; struct in_device *in_dev; int err; rtnl_lock(); - if (np->dev_name[0]) { - struct net *net = current->nsproxy->net_ns; + if (np->dev_name[0]) ndev = __dev_get_by_name(net, np->dev_name); - } + else if (is_valid_ether_addr(np->dev_mac)) + ndev = dev_getbyhwaddr(net, ARPHRD_ETHER, np->dev_mac); + if (!ndev) { - np_err(np, "%s doesn't exist, aborting\n", np->dev_name); + np_err(np, "%s doesn't exist, aborting\n", egress_dev(np, buf)); err = -ENODEV; goto unlock; } netdev_hold(ndev, &np->dev_tracker, GFP_KERNEL); if (netdev_master_upper_dev_get(ndev)) { - np_err(np, "%s is a slave device, aborting\n", np->dev_name); + np_err(np, "%s is a slave device, aborting\n", + egress_dev(np, buf)); err = -EBUSY; goto put; } @@ -707,7 +748,8 @@ int netpoll_setup(struct netpoll *np) if (!netif_running(ndev)) { unsigned long atmost; - np_info(np, "device %s not up yet, forcing it\n", np->dev_name); + np_info(np, "device %s not up yet, forcing it\n", + egress_dev(np, buf)); err = dev_open(ndev, NULL); @@ -741,7 +783,7 @@ int netpoll_setup(struct netpoll *np) if (!ifa) { put_noaddr: np_err(np, "no IP address for %s, aborting\n", - np->dev_name); + egress_dev(np, buf)); err = -EDESTADDRREQ; goto put; } @@ -772,13 +814,13 @@ put_noaddr: } if (err) { np_err(np, "no IPv6 address for %s, aborting\n", - np->dev_name); + egress_dev(np, buf)); goto put; } else np_info(np, "local IPv6 %pI6c\n", &np->local_ip.in6); #else np_err(np, "IPv6 is not supported %s, aborting\n", - np->dev_name); + egress_dev(np, buf)); err = -EINVAL; goto put; #endif diff --git a/net/core/page_pool.c b/net/core/page_pool.c index f5e908c9e7ad..7745ad924ae2 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -11,8 +11,10 @@ #include <linux/slab.h> #include <linux/device.h> +#include <net/netdev_lock.h> #include <net/netdev_rx_queue.h> #include <net/page_pool/helpers.h> +#include <net/page_pool/memory_provider.h> #include <net/xdp.h> #include <linux/dma-direction.h> @@ -25,6 +27,7 @@ #include <trace/events/page_pool.h> +#include "dev.h" #include "mp_dmabuf_devmem.h" #include "netmem_priv.h" #include "page_pool_priv.h" @@ -277,21 +280,23 @@ static int page_pool_init(struct page_pool *pool, get_device(pool->p.dev); if (pool->slow.flags & PP_FLAG_ALLOW_UNREADABLE_NETMEM) { - /* We rely on rtnl_lock()ing to make sure netdev_rx_queue - * configuration doesn't change while we're initializing - * the page_pool. - */ - ASSERT_RTNL(); + netdev_assert_locked(pool->slow.netdev); rxq = __netif_get_rx_queue(pool->slow.netdev, pool->slow.queue_idx); pool->mp_priv = rxq->mp_params.mp_priv; + pool->mp_ops = rxq->mp_params.mp_ops; } - if (pool->mp_priv) { + if (pool->mp_ops) { if (!pool->dma_map || !pool->dma_sync) return -EOPNOTSUPP; - err = mp_dmabuf_devmem_init(pool); + if (WARN_ON(!is_kernel_rodata((unsigned long)pool->mp_ops))) { + err = -EFAULT; + goto free_ptr_ring; + } + + err = pool->mp_ops->init(pool); if (err) { pr_warn("%s() mem-provider init failed %d\n", __func__, err); @@ -587,8 +592,8 @@ netmem_ref page_pool_alloc_netmems(struct page_pool *pool, gfp_t gfp) return netmem; /* Slow-path: cache empty, do real allocation */ - if (static_branch_unlikely(&page_pool_mem_providers) && pool->mp_priv) - netmem = mp_dmabuf_devmem_alloc_netmems(pool, gfp); + if (static_branch_unlikely(&page_pool_mem_providers) && pool->mp_ops) + netmem = pool->mp_ops->alloc_netmems(pool, gfp); else netmem = __page_pool_alloc_pages_slow(pool, gfp); return netmem; @@ -679,8 +684,8 @@ void page_pool_return_page(struct page_pool *pool, netmem_ref netmem) bool put; put = true; - if (static_branch_unlikely(&page_pool_mem_providers) && pool->mp_priv) - put = mp_dmabuf_devmem_release_page(pool, netmem); + if (static_branch_unlikely(&page_pool_mem_providers) && pool->mp_ops) + put = pool->mp_ops->release_netmem(pool, netmem); else __page_pool_release_page_dma(pool, netmem); @@ -1048,8 +1053,8 @@ static void __page_pool_destroy(struct page_pool *pool) page_pool_unlist(pool); page_pool_uninit(pool); - if (pool->mp_priv) { - mp_dmabuf_devmem_destroy(pool); + if (pool->mp_ops) { + pool->mp_ops->destroy(pool); static_branch_dec(&page_pool_mem_providers); } @@ -1104,7 +1109,13 @@ static void page_pool_release_retry(struct work_struct *wq) int inflight; inflight = page_pool_release(pool); - if (!inflight) + /* In rare cases, a driver bug may cause inflight to go negative. + * Don't reschedule release if inflight is 0 or negative. + * - If 0, the page_pool has been destroyed + * - if negative, we will never recover + * in both cases no reschedule is necessary. + */ + if (inflight <= 0) return; /* Periodic warning for page pools the user can't see */ @@ -1140,11 +1151,7 @@ void page_pool_disable_direct_recycling(struct page_pool *pool) if (!pool->p.napi) return; - /* To avoid races with recycling and additional barriers make sure - * pool and NAPI are unlinked when NAPI is disabled. - */ - WARN_ON(!test_bit(NAPI_STATE_SCHED, &pool->p.napi->state)); - WARN_ON(READ_ONCE(pool->p.napi->list_owner) != -1); + napi_assert_will_not_race(pool->p.napi); mutex_lock(&page_pools_lock); WRITE_ONCE(pool->p.napi, NULL); @@ -1190,3 +1197,31 @@ void page_pool_update_nid(struct page_pool *pool, int new_nid) } } EXPORT_SYMBOL(page_pool_update_nid); + +bool net_mp_niov_set_dma_addr(struct net_iov *niov, dma_addr_t addr) +{ + return page_pool_set_dma_addr_netmem(net_iov_to_netmem(niov), addr); +} + +/* Associate a niov with a page pool. Should follow with a matching + * net_mp_niov_clear_page_pool() + */ +void net_mp_niov_set_page_pool(struct page_pool *pool, struct net_iov *niov) +{ + netmem_ref netmem = net_iov_to_netmem(niov); + + page_pool_set_pp_info(pool, netmem); + + pool->pages_state_hold_cnt++; + trace_page_pool_state_hold(pool, netmem, pool->pages_state_hold_cnt); +} + +/* Disassociate a niov from a page pool. Should only be used in the + * ->release_netmem() path. + */ +void net_mp_niov_clear_page_pool(struct net_iov *niov) +{ + netmem_ref netmem = net_iov_to_netmem(niov); + + page_pool_clear_pp_info(netmem); +} diff --git a/net/core/page_pool_user.c b/net/core/page_pool_user.c index 6677e0c2e256..c82a95beceff 100644 --- a/net/core/page_pool_user.c +++ b/net/core/page_pool_user.c @@ -8,9 +8,9 @@ #include <net/netdev_rx_queue.h> #include <net/page_pool/helpers.h> #include <net/page_pool/types.h> +#include <net/page_pool/memory_provider.h> #include <net/sock.h> -#include "devmem.h" #include "page_pool_priv.h" #include "netdev-genl-gen.h" @@ -216,7 +216,6 @@ static int page_pool_nl_fill(struct sk_buff *rsp, const struct page_pool *pool, const struct genl_info *info) { - struct net_devmem_dmabuf_binding *binding = pool->mp_priv; size_t inflight, refsz; unsigned int napi_id; void *hdr; @@ -234,7 +233,7 @@ page_pool_nl_fill(struct sk_buff *rsp, const struct page_pool *pool, goto err_cancel; napi_id = pool->p.napi ? READ_ONCE(pool->p.napi->napi_id) : 0; - if (napi_id >= MIN_NAPI_ID && + if (napi_id_valid(napi_id) && nla_put_uint(rsp, NETDEV_A_PAGE_POOL_NAPI_ID, napi_id)) goto err_cancel; @@ -249,7 +248,7 @@ page_pool_nl_fill(struct sk_buff *rsp, const struct page_pool *pool, pool->user.detach_time)) goto err_cancel; - if (binding && nla_put_u32(rsp, NETDEV_A_PAGE_POOL_DMABUF, binding->id)) + if (pool->mp_ops && pool->mp_ops->nl_fill(pool->mp_priv, rsp, NULL)) goto err_cancel; genlmsg_end(rsp, hdr); @@ -356,7 +355,7 @@ void page_pool_unlist(struct page_pool *pool) int page_pool_check_memory_provider(struct net_device *dev, struct netdev_rx_queue *rxq) { - struct net_devmem_dmabuf_binding *binding = rxq->mp_params.mp_priv; + void *binding = rxq->mp_params.mp_priv; struct page_pool *pool; struct hlist_node *n; diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 82b6a2c3c141..fe7fdefab994 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -158,9 +158,7 @@ #include <net/udp.h> #include <net/ip6_checksum.h> #include <net/addrconf.h> -#ifdef CONFIG_XFRM #include <net/xfrm.h> -#endif #include <net/netns/generic.h> #include <asm/byteorder.h> #include <linux/rcupdate.h> @@ -517,21 +515,23 @@ static ssize_t pgctrl_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { char data[128]; + size_t max; struct pktgen_net *pn = net_generic(current->nsproxy->net_ns, pg_net_id); if (!capable(CAP_NET_ADMIN)) return -EPERM; - if (count == 0) + if (count < 1) return -EINVAL; - if (count > sizeof(data)) - count = sizeof(data); - - if (copy_from_user(data, buf, count)) + max = min(count, sizeof(data) - 1); + if (copy_from_user(data, buf, max)) return -EFAULT; - data[count - 1] = 0; /* Strip trailing '\n' and terminate string */ + if (data[max - 1] == '\n') + data[max - 1] = 0; /* strip trailing '\n', terminate string */ + else + data[max] = 0; /* terminate string */ if (!strcmp(data, "stop")) pktgen_stop_all_threads(pn); @@ -744,31 +744,32 @@ static int pktgen_if_show(struct seq_file *seq, void *v) } -static int hex32_arg(const char __user *user_buffer, unsigned long maxlen, - __u32 *num) +static ssize_t hex32_arg(const char __user *user_buffer, size_t maxlen, + __u32 *num) { - int i = 0; + size_t i = 0; + *num = 0; for (; i < maxlen; i++) { int value; char c; - *num <<= 4; if (get_user(c, &user_buffer[i])) return -EFAULT; value = hex_to_bin(c); - if (value >= 0) + if (value >= 0) { + *num <<= 4; *num |= value; - else + } else { break; + } } return i; } -static int count_trail_chars(const char __user * user_buffer, - unsigned int maxlen) +static ssize_t count_trail_chars(const char __user *user_buffer, size_t maxlen) { - int i; + size_t i; for (i = 0; i < maxlen; i++) { char c; @@ -790,10 +791,10 @@ done: return i; } -static long num_arg(const char __user *user_buffer, unsigned long maxlen, - unsigned long *num) +static ssize_t num_arg(const char __user *user_buffer, size_t maxlen, + unsigned long *num) { - int i; + size_t i; *num = 0; for (i = 0; i < maxlen; i++) { @@ -809,9 +810,9 @@ static long num_arg(const char __user *user_buffer, unsigned long maxlen, return i; } -static int strn_len(const char __user * user_buffer, unsigned int maxlen) +static ssize_t strn_len(const char __user *user_buffer, size_t maxlen) { - int i; + size_t i; for (i = 0; i < maxlen; i++) { char c; @@ -823,6 +824,7 @@ static int strn_len(const char __user * user_buffer, unsigned int maxlen) case '\r': case '\t': case ' ': + case '=': goto done_str; default: break; @@ -838,11 +840,11 @@ done_str: * "size1,weight_1 size2,weight_2 ... size_n,weight_n" for example. */ static ssize_t get_imix_entries(const char __user *buffer, + size_t maxlen, struct pktgen_dev *pkt_dev) { - const int max_digits = 10; - int i = 0; - long len; + size_t i = 0, max; + ssize_t len; char c; pkt_dev->n_imix_entries = 0; @@ -854,21 +856,30 @@ static ssize_t get_imix_entries(const char __user *buffer, if (pkt_dev->n_imix_entries >= MAX_IMIX_ENTRIES) return -E2BIG; - len = num_arg(&buffer[i], max_digits, &size); + if (i >= maxlen) + return -EINVAL; + + max = min(10, maxlen - i); + len = num_arg(&buffer[i], max, &size); if (len < 0) return len; i += len; + if (i >= maxlen) + return -EINVAL; if (get_user(c, &buffer[i])) return -EFAULT; /* Check for comma between size_i and weight_i */ if (c != ',') return -EINVAL; i++; + if (i >= maxlen) + return -EINVAL; if (size < 14 + 20 + 8) size = 14 + 20 + 8; - len = num_arg(&buffer[i], max_digits, &weight); + max = min(10, maxlen - i); + len = num_arg(&buffer[i], max, &weight); if (len < 0) return len; if (weight <= 0) @@ -878,39 +889,55 @@ static ssize_t get_imix_entries(const char __user *buffer, pkt_dev->imix_entries[pkt_dev->n_imix_entries].weight = weight; i += len; + pkt_dev->n_imix_entries++; + + if (i >= maxlen) + break; if (get_user(c, &buffer[i])) return -EFAULT; - i++; - pkt_dev->n_imix_entries++; } while (c == ' '); return i; } -static ssize_t get_labels(const char __user *buffer, struct pktgen_dev *pkt_dev) +static ssize_t get_labels(const char __user *buffer, + size_t maxlen, struct pktgen_dev *pkt_dev) { unsigned int n = 0; + size_t i = 0, max; + ssize_t len; char c; - ssize_t i = 0; - int len; pkt_dev->nr_labels = 0; do { __u32 tmp; - len = hex32_arg(&buffer[i], 8, &tmp); - if (len <= 0) + + if (n >= MAX_MPLS_LABELS) + return -E2BIG; + + if (i >= maxlen) + return -EINVAL; + + max = min(8, maxlen - i); + len = hex32_arg(&buffer[i], max, &tmp); + if (len < 0) return len; + + /* return empty list in case of invalid input or zero value */ + if (len == 0 || tmp == 0) + return maxlen; + pkt_dev->labels[n] = htonl(tmp); if (pkt_dev->labels[n] & MPLS_STACK_BOTTOM) pkt_dev->flags |= F_MPLS_RND; i += len; + n++; + if (i >= maxlen) + break; if (get_user(c, &buffer[i])) return -EFAULT; i++; - n++; - if (n >= MAX_MPLS_LABELS) - return -E2BIG; } while (c == ','); pkt_dev->nr_labels = n; @@ -952,11 +979,11 @@ static ssize_t pktgen_if_write(struct file *file, { struct seq_file *seq = file->private_data; struct pktgen_dev *pkt_dev = seq->private; - int i, max, len; + size_t i, max; + ssize_t len; char name[16], valstr[32]; unsigned long value = 0; char *pg_result = NULL; - int tmp = 0; char buf[128]; pg_result = &(pkt_dev->result[0]); @@ -967,16 +994,16 @@ static ssize_t pktgen_if_write(struct file *file, } max = count; - tmp = count_trail_chars(user_buffer, max); - if (tmp < 0) { + len = count_trail_chars(user_buffer, max); + if (len < 0) { pr_warn("illegal format\n"); - return tmp; + return len; } - i = tmp; + i = len; /* Read variable name */ - - len = strn_len(&user_buffer[i], sizeof(name) - 1); + max = min(sizeof(name) - 1, count - i); + len = strn_len(&user_buffer[i], max); if (len < 0) return len; @@ -1004,11 +1031,11 @@ static ssize_t pktgen_if_write(struct file *file, } if (!strcmp(name, "min_pkt_size")) { - len = num_arg(&user_buffer[i], 10, &value); + max = min(10, count - i); + len = num_arg(&user_buffer[i], max, &value); if (len < 0) return len; - i += len; if (value < 14 + 20 + 8) value = 14 + 20 + 8; if (value != pkt_dev->min_pkt_size) { @@ -1021,11 +1048,11 @@ static ssize_t pktgen_if_write(struct file *file, } if (!strcmp(name, "max_pkt_size")) { - len = num_arg(&user_buffer[i], 10, &value); + max = min(10, count - i); + len = num_arg(&user_buffer[i], max, &value); if (len < 0) return len; - i += len; if (value < 14 + 20 + 8) value = 14 + 20 + 8; if (value != pkt_dev->max_pkt_size) { @@ -1040,11 +1067,11 @@ static ssize_t pktgen_if_write(struct file *file, /* Shortcut for min = max */ if (!strcmp(name, "pkt_size")) { - len = num_arg(&user_buffer[i], 10, &value); + max = min(10, count - i); + len = num_arg(&user_buffer[i], max, &value); if (len < 0) return len; - i += len; if (value < 14 + 20 + 8) value = 14 + 20 + 8; if (value != pkt_dev->min_pkt_size) { @@ -1060,43 +1087,43 @@ static ssize_t pktgen_if_write(struct file *file, if (pkt_dev->clone_skb > 0) return -EINVAL; - len = get_imix_entries(&user_buffer[i], pkt_dev); + max = count - i; + len = get_imix_entries(&user_buffer[i], max, pkt_dev); if (len < 0) return len; fill_imix_distribution(pkt_dev); - i += len; return count; } if (!strcmp(name, "debug")) { - len = num_arg(&user_buffer[i], 10, &value); + max = min(10, count - i); + len = num_arg(&user_buffer[i], max, &value); if (len < 0) return len; - i += len; debug = value; sprintf(pg_result, "OK: debug=%u", debug); return count; } if (!strcmp(name, "frags")) { - len = num_arg(&user_buffer[i], 10, &value); + max = min(10, count - i); + len = num_arg(&user_buffer[i], max, &value); if (len < 0) return len; - i += len; pkt_dev->nfrags = value; sprintf(pg_result, "OK: frags=%d", pkt_dev->nfrags); return count; } if (!strcmp(name, "delay")) { - len = num_arg(&user_buffer[i], 10, &value); + max = min(10, count - i); + len = num_arg(&user_buffer[i], max, &value); if (len < 0) return len; - i += len; if (value == 0x7FFFFFFF) pkt_dev->delay = ULLONG_MAX; else @@ -1107,13 +1134,13 @@ static ssize_t pktgen_if_write(struct file *file, return count; } if (!strcmp(name, "rate")) { - len = num_arg(&user_buffer[i], 10, &value); + max = min(10, count - i); + len = num_arg(&user_buffer[i], max, &value); if (len < 0) return len; - i += len; if (!value) - return len; + return -EINVAL; pkt_dev->delay = pkt_dev->min_pkt_size*8*NSEC_PER_USEC/value; if (debug) pr_info("Delay set at: %llu ns\n", pkt_dev->delay); @@ -1122,13 +1149,13 @@ static ssize_t pktgen_if_write(struct file *file, return count; } if (!strcmp(name, "ratep")) { - len = num_arg(&user_buffer[i], 10, &value); + max = min(10, count - i); + len = num_arg(&user_buffer[i], max, &value); if (len < 0) return len; - i += len; if (!value) - return len; + return -EINVAL; pkt_dev->delay = NSEC_PER_SEC/value; if (debug) pr_info("Delay set at: %llu ns\n", pkt_dev->delay); @@ -1137,11 +1164,11 @@ static ssize_t pktgen_if_write(struct file *file, return count; } if (!strcmp(name, "udp_src_min")) { - len = num_arg(&user_buffer[i], 10, &value); + max = min(10, count - i); + len = num_arg(&user_buffer[i], max, &value); if (len < 0) return len; - i += len; if (value != pkt_dev->udp_src_min) { pkt_dev->udp_src_min = value; pkt_dev->cur_udp_src = value; @@ -1150,11 +1177,11 @@ static ssize_t pktgen_if_write(struct file *file, return count; } if (!strcmp(name, "udp_dst_min")) { - len = num_arg(&user_buffer[i], 10, &value); + max = min(10, count - i); + len = num_arg(&user_buffer[i], max, &value); if (len < 0) return len; - i += len; if (value != pkt_dev->udp_dst_min) { pkt_dev->udp_dst_min = value; pkt_dev->cur_udp_dst = value; @@ -1163,11 +1190,11 @@ static ssize_t pktgen_if_write(struct file *file, return count; } if (!strcmp(name, "udp_src_max")) { - len = num_arg(&user_buffer[i], 10, &value); + max = min(10, count - i); + len = num_arg(&user_buffer[i], max, &value); if (len < 0) return len; - i += len; if (value != pkt_dev->udp_src_max) { pkt_dev->udp_src_max = value; pkt_dev->cur_udp_src = value; @@ -1176,11 +1203,11 @@ static ssize_t pktgen_if_write(struct file *file, return count; } if (!strcmp(name, "udp_dst_max")) { - len = num_arg(&user_buffer[i], 10, &value); + max = min(10, count - i); + len = num_arg(&user_buffer[i], max, &value); if (len < 0) return len; - i += len; if (value != pkt_dev->udp_dst_max) { pkt_dev->udp_dst_max = value; pkt_dev->cur_udp_dst = value; @@ -1189,7 +1216,8 @@ static ssize_t pktgen_if_write(struct file *file, return count; } if (!strcmp(name, "clone_skb")) { - len = num_arg(&user_buffer[i], 10, &value); + max = min(10, count - i); + len = num_arg(&user_buffer[i], max, &value); if (len < 0) return len; /* clone_skb is not supported for netif_receive xmit_mode and @@ -1198,34 +1226,33 @@ static ssize_t pktgen_if_write(struct file *file, if ((value > 0) && ((pkt_dev->xmit_mode == M_NETIF_RECEIVE) || !(pkt_dev->odev->priv_flags & IFF_TX_SKB_SHARING))) - return -ENOTSUPP; + return -EOPNOTSUPP; if (value > 0 && (pkt_dev->n_imix_entries > 0 || !(pkt_dev->flags & F_SHARED))) return -EINVAL; - i += len; pkt_dev->clone_skb = value; sprintf(pg_result, "OK: clone_skb=%d", pkt_dev->clone_skb); return count; } if (!strcmp(name, "count")) { - len = num_arg(&user_buffer[i], 10, &value); + max = min(10, count - i); + len = num_arg(&user_buffer[i], max, &value); if (len < 0) return len; - i += len; pkt_dev->count = value; sprintf(pg_result, "OK: count=%llu", (unsigned long long)pkt_dev->count); return count; } if (!strcmp(name, "src_mac_count")) { - len = num_arg(&user_buffer[i], 10, &value); + max = min(10, count - i); + len = num_arg(&user_buffer[i], max, &value); if (len < 0) return len; - i += len; if (pkt_dev->src_mac_count != value) { pkt_dev->src_mac_count = value; pkt_dev->cur_src_mac_offset = 0; @@ -1235,11 +1262,11 @@ static ssize_t pktgen_if_write(struct file *file, return count; } if (!strcmp(name, "dst_mac_count")) { - len = num_arg(&user_buffer[i], 10, &value); + max = min(10, count - i); + len = num_arg(&user_buffer[i], max, &value); if (len < 0) return len; - i += len; if (pkt_dev->dst_mac_count != value) { pkt_dev->dst_mac_count = value; pkt_dev->cur_dst_mac_offset = 0; @@ -1249,16 +1276,16 @@ static ssize_t pktgen_if_write(struct file *file, return count; } if (!strcmp(name, "burst")) { - len = num_arg(&user_buffer[i], 10, &value); + max = min(10, count - i); + len = num_arg(&user_buffer[i], max, &value); if (len < 0) return len; - i += len; if ((value > 1) && ((pkt_dev->xmit_mode == M_QUEUE_XMIT) || ((pkt_dev->xmit_mode == M_START_XMIT) && (!(pkt_dev->odev->priv_flags & IFF_TX_SKB_SHARING))))) - return -ENOTSUPP; + return -EOPNOTSUPP; if (value > 1 && !(pkt_dev->flags & F_SHARED)) return -EINVAL; @@ -1268,12 +1295,11 @@ static ssize_t pktgen_if_write(struct file *file, return count; } if (!strcmp(name, "node")) { - len = num_arg(&user_buffer[i], 10, &value); + max = min(10, count - i); + len = num_arg(&user_buffer[i], max, &value); if (len < 0) return len; - i += len; - if (node_possible(value)) { pkt_dev->node = value; sprintf(pg_result, "OK: node=%d", pkt_dev->node); @@ -1289,21 +1315,21 @@ static ssize_t pktgen_if_write(struct file *file, if (!strcmp(name, "xmit_mode")) { char f[32]; - memset(f, 0, 32); - len = strn_len(&user_buffer[i], sizeof(f) - 1); + max = min(sizeof(f) - 1, count - i); + len = strn_len(&user_buffer[i], max); if (len < 0) return len; + memset(f, 0, sizeof(f)); if (copy_from_user(f, &user_buffer[i], len)) return -EFAULT; - i += len; if (strcmp(f, "start_xmit") == 0) { pkt_dev->xmit_mode = M_START_XMIT; } else if (strcmp(f, "netif_receive") == 0) { /* clone_skb set earlier, not supported in this mode */ if (pkt_dev->clone_skb > 0) - return -ENOTSUPP; + return -EOPNOTSUPP; pkt_dev->xmit_mode = M_NETIF_RECEIVE; @@ -1329,14 +1355,14 @@ static ssize_t pktgen_if_write(struct file *file, char f[32]; char *end; - memset(f, 0, 32); - len = strn_len(&user_buffer[i], sizeof(f) - 1); + max = min(sizeof(f) - 1, count - i); + len = strn_len(&user_buffer[i], max); if (len < 0) return len; + memset(f, 0, 32); if (copy_from_user(f, &user_buffer[i], len)) return -EFAULT; - i += len; flag = pktgen_read_flag(f, &disable); if (flag) { @@ -1378,7 +1404,8 @@ static ssize_t pktgen_if_write(struct file *file, return count; } if (!strcmp(name, "dst_min") || !strcmp(name, "dst")) { - len = strn_len(&user_buffer[i], sizeof(pkt_dev->dst_min) - 1); + max = min(sizeof(pkt_dev->dst_min) - 1, count - i); + len = strn_len(&user_buffer[i], max); if (len < 0) return len; @@ -1393,12 +1420,13 @@ static ssize_t pktgen_if_write(struct file *file, } if (debug) pr_debug("dst_min set to: %s\n", pkt_dev->dst_min); - i += len; + sprintf(pg_result, "OK: dst_min=%s", pkt_dev->dst_min); return count; } if (!strcmp(name, "dst_max")) { - len = strn_len(&user_buffer[i], sizeof(pkt_dev->dst_max) - 1); + max = min(sizeof(pkt_dev->dst_max) - 1, count - i); + len = strn_len(&user_buffer[i], max); if (len < 0) return len; @@ -1413,12 +1441,13 @@ static ssize_t pktgen_if_write(struct file *file, } if (debug) pr_debug("dst_max set to: %s\n", pkt_dev->dst_max); - i += len; + sprintf(pg_result, "OK: dst_max=%s", pkt_dev->dst_max); return count; } if (!strcmp(name, "dst6")) { - len = strn_len(&user_buffer[i], sizeof(buf) - 1); + max = min(sizeof(buf) - 1, count - i); + len = strn_len(&user_buffer[i], max); if (len < 0) return len; @@ -1436,12 +1465,12 @@ static ssize_t pktgen_if_write(struct file *file, if (debug) pr_debug("dst6 set to: %s\n", buf); - i += len; sprintf(pg_result, "OK: dst6=%s", buf); return count; } if (!strcmp(name, "dst6_min")) { - len = strn_len(&user_buffer[i], sizeof(buf) - 1); + max = min(sizeof(buf) - 1, count - i); + len = strn_len(&user_buffer[i], max); if (len < 0) return len; @@ -1458,12 +1487,12 @@ static ssize_t pktgen_if_write(struct file *file, if (debug) pr_debug("dst6_min set to: %s\n", buf); - i += len; sprintf(pg_result, "OK: dst6_min=%s", buf); return count; } if (!strcmp(name, "dst6_max")) { - len = strn_len(&user_buffer[i], sizeof(buf) - 1); + max = min(sizeof(buf) - 1, count - i); + len = strn_len(&user_buffer[i], max); if (len < 0) return len; @@ -1479,12 +1508,12 @@ static ssize_t pktgen_if_write(struct file *file, if (debug) pr_debug("dst6_max set to: %s\n", buf); - i += len; sprintf(pg_result, "OK: dst6_max=%s", buf); return count; } if (!strcmp(name, "src6")) { - len = strn_len(&user_buffer[i], sizeof(buf) - 1); + max = min(sizeof(buf) - 1, count - i); + len = strn_len(&user_buffer[i], max); if (len < 0) return len; @@ -1502,12 +1531,12 @@ static ssize_t pktgen_if_write(struct file *file, if (debug) pr_debug("src6 set to: %s\n", buf); - i += len; sprintf(pg_result, "OK: src6=%s", buf); return count; } if (!strcmp(name, "src_min")) { - len = strn_len(&user_buffer[i], sizeof(pkt_dev->src_min) - 1); + max = min(sizeof(pkt_dev->src_min) - 1, count - i); + len = strn_len(&user_buffer[i], max); if (len < 0) return len; @@ -1522,12 +1551,13 @@ static ssize_t pktgen_if_write(struct file *file, } if (debug) pr_debug("src_min set to: %s\n", pkt_dev->src_min); - i += len; + sprintf(pg_result, "OK: src_min=%s", pkt_dev->src_min); return count; } if (!strcmp(name, "src_max")) { - len = strn_len(&user_buffer[i], sizeof(pkt_dev->src_max) - 1); + max = min(sizeof(pkt_dev->src_max) - 1, count - i); + len = strn_len(&user_buffer[i], max); if (len < 0) return len; @@ -1542,12 +1572,13 @@ static ssize_t pktgen_if_write(struct file *file, } if (debug) pr_debug("src_max set to: %s\n", pkt_dev->src_max); - i += len; + sprintf(pg_result, "OK: src_max=%s", pkt_dev->src_max); return count; } if (!strcmp(name, "dst_mac")) { - len = strn_len(&user_buffer[i], sizeof(valstr) - 1); + max = min(sizeof(valstr) - 1, count - i); + len = strn_len(&user_buffer[i], max); if (len < 0) return len; @@ -1564,7 +1595,8 @@ static ssize_t pktgen_if_write(struct file *file, return count; } if (!strcmp(name, "src_mac")) { - len = strn_len(&user_buffer[i], sizeof(valstr) - 1); + max = min(sizeof(valstr) - 1, count - i); + len = strn_len(&user_buffer[i], max); if (len < 0) return len; @@ -1588,11 +1620,11 @@ static ssize_t pktgen_if_write(struct file *file, } if (!strcmp(name, "flows")) { - len = num_arg(&user_buffer[i], 10, &value); + max = min(10, count - i); + len = num_arg(&user_buffer[i], max, &value); if (len < 0) return len; - i += len; if (value > MAX_CFLOWS) value = MAX_CFLOWS; @@ -1602,44 +1634,44 @@ static ssize_t pktgen_if_write(struct file *file, } #ifdef CONFIG_XFRM if (!strcmp(name, "spi")) { - len = num_arg(&user_buffer[i], 10, &value); + max = min(10, count - i); + len = num_arg(&user_buffer[i], max, &value); if (len < 0) return len; - i += len; pkt_dev->spi = value; sprintf(pg_result, "OK: spi=%u", pkt_dev->spi); return count; } #endif if (!strcmp(name, "flowlen")) { - len = num_arg(&user_buffer[i], 10, &value); + max = min(10, count - i); + len = num_arg(&user_buffer[i], max, &value); if (len < 0) return len; - i += len; pkt_dev->lflow = value; sprintf(pg_result, "OK: flowlen=%u", pkt_dev->lflow); return count; } if (!strcmp(name, "queue_map_min")) { - len = num_arg(&user_buffer[i], 5, &value); + max = min(5, count - i); + len = num_arg(&user_buffer[i], max, &value); if (len < 0) return len; - i += len; pkt_dev->queue_map_min = value; sprintf(pg_result, "OK: queue_map_min=%u", pkt_dev->queue_map_min); return count; } if (!strcmp(name, "queue_map_max")) { - len = num_arg(&user_buffer[i], 5, &value); + max = min(5, count - i); + len = num_arg(&user_buffer[i], max, &value); if (len < 0) return len; - i += len; pkt_dev->queue_map_max = value; sprintf(pg_result, "OK: queue_map_max=%u", pkt_dev->queue_map_max); return count; @@ -1648,10 +1680,11 @@ static ssize_t pktgen_if_write(struct file *file, if (!strcmp(name, "mpls")) { unsigned int n, cnt; - len = get_labels(&user_buffer[i], pkt_dev); + max = count - i; + len = get_labels(&user_buffer[i], max, pkt_dev); if (len < 0) return len; - i += len; + cnt = sprintf(pg_result, "OK: mpls="); for (n = 0; n < pkt_dev->nr_labels; n++) cnt += sprintf(pg_result + cnt, @@ -1669,11 +1702,11 @@ static ssize_t pktgen_if_write(struct file *file, } if (!strcmp(name, "vlan_id")) { - len = num_arg(&user_buffer[i], 4, &value); + max = min(4, count - i); + len = num_arg(&user_buffer[i], max, &value); if (len < 0) return len; - i += len; if (value <= 4095) { pkt_dev->vlan_id = value; /* turn on VLAN */ @@ -1696,11 +1729,11 @@ static ssize_t pktgen_if_write(struct file *file, } if (!strcmp(name, "vlan_p")) { - len = num_arg(&user_buffer[i], 1, &value); + max = min(1, count - i); + len = num_arg(&user_buffer[i], max, &value); if (len < 0) return len; - i += len; if ((value <= 7) && (pkt_dev->vlan_id != 0xffff)) { pkt_dev->vlan_p = value; sprintf(pg_result, "OK: vlan_p=%u", pkt_dev->vlan_p); @@ -1711,11 +1744,11 @@ static ssize_t pktgen_if_write(struct file *file, } if (!strcmp(name, "vlan_cfi")) { - len = num_arg(&user_buffer[i], 1, &value); + max = min(1, count - i); + len = num_arg(&user_buffer[i], max, &value); if (len < 0) return len; - i += len; if ((value <= 1) && (pkt_dev->vlan_id != 0xffff)) { pkt_dev->vlan_cfi = value; sprintf(pg_result, "OK: vlan_cfi=%u", pkt_dev->vlan_cfi); @@ -1726,11 +1759,11 @@ static ssize_t pktgen_if_write(struct file *file, } if (!strcmp(name, "svlan_id")) { - len = num_arg(&user_buffer[i], 4, &value); + max = min(4, count - i); + len = num_arg(&user_buffer[i], max, &value); if (len < 0) return len; - i += len; if ((value <= 4095) && ((pkt_dev->vlan_id != 0xffff))) { pkt_dev->svlan_id = value; /* turn on SVLAN */ @@ -1753,11 +1786,11 @@ static ssize_t pktgen_if_write(struct file *file, } if (!strcmp(name, "svlan_p")) { - len = num_arg(&user_buffer[i], 1, &value); + max = min(1, count - i); + len = num_arg(&user_buffer[i], max, &value); if (len < 0) return len; - i += len; if ((value <= 7) && (pkt_dev->svlan_id != 0xffff)) { pkt_dev->svlan_p = value; sprintf(pg_result, "OK: svlan_p=%u", pkt_dev->svlan_p); @@ -1768,11 +1801,11 @@ static ssize_t pktgen_if_write(struct file *file, } if (!strcmp(name, "svlan_cfi")) { - len = num_arg(&user_buffer[i], 1, &value); + max = min(1, count - i); + len = num_arg(&user_buffer[i], max, &value); if (len < 0) return len; - i += len; if ((value <= 1) && (pkt_dev->svlan_id != 0xffff)) { pkt_dev->svlan_cfi = value; sprintf(pg_result, "OK: svlan_cfi=%u", pkt_dev->svlan_cfi); @@ -1783,12 +1816,13 @@ static ssize_t pktgen_if_write(struct file *file, } if (!strcmp(name, "tos")) { - __u32 tmp_value = 0; - len = hex32_arg(&user_buffer[i], 2, &tmp_value); + __u32 tmp_value; + + max = min(2, count - i); + len = hex32_arg(&user_buffer[i], max, &tmp_value); if (len < 0) return len; - i += len; if (len == 2) { pkt_dev->tos = tmp_value; sprintf(pg_result, "OK: tos=0x%02x", pkt_dev->tos); @@ -1799,12 +1833,13 @@ static ssize_t pktgen_if_write(struct file *file, } if (!strcmp(name, "traffic_class")) { - __u32 tmp_value = 0; - len = hex32_arg(&user_buffer[i], 2, &tmp_value); + __u32 tmp_value; + + max = min(2, count - i); + len = hex32_arg(&user_buffer[i], max, &tmp_value); if (len < 0) return len; - i += len; if (len == 2) { pkt_dev->traffic_class = tmp_value; sprintf(pg_result, "OK: traffic_class=0x%02x", pkt_dev->traffic_class); @@ -1815,11 +1850,11 @@ static ssize_t pktgen_if_write(struct file *file, } if (!strcmp(name, "skb_priority")) { - len = num_arg(&user_buffer[i], 9, &value); + max = min(9, count - i); + len = num_arg(&user_buffer[i], max, &value); if (len < 0) return len; - i += len; pkt_dev->skb_priority = value; sprintf(pg_result, "OK: skb_priority=%i", pkt_dev->skb_priority); @@ -1879,7 +1914,8 @@ static ssize_t pktgen_thread_write(struct file *file, { struct seq_file *seq = file->private_data; struct pktgen_thread *t = seq->private; - int i, max, len, ret; + size_t i, max; + ssize_t len, ret; char name[40]; char *pg_result; @@ -1896,8 +1932,8 @@ static ssize_t pktgen_thread_write(struct file *file, i = len; /* Read variable name */ - - len = strn_len(&user_buffer[i], sizeof(name) - 1); + max = min(sizeof(name) - 1, count - i); + len = strn_len(&user_buffer[i], max); if (len < 0) return len; @@ -1927,14 +1963,15 @@ static ssize_t pktgen_thread_write(struct file *file, if (!strcmp(name, "add_device")) { char f[32]; memset(f, 0, 32); - len = strn_len(&user_buffer[i], sizeof(f) - 1); + max = min(sizeof(f) - 1, count - i); + len = strn_len(&user_buffer[i], max); if (len < 0) { ret = len; goto out; } if (copy_from_user(f, &user_buffer[i], len)) return -EFAULT; - i += len; + mutex_lock(&pktgen_thread_lock); ret = pktgen_add_device(t, f); mutex_unlock(&pktgen_thread_lock); @@ -2358,13 +2395,13 @@ static inline int f_pick(struct pktgen_dev *pkt_dev) } -#ifdef CONFIG_XFRM /* If there was already an IPSEC SA, we keep it as is, else * we go look for it ... */ #define DUMMY_MARK 0 static void get_ipsec_sa(struct pktgen_dev *pkt_dev, int flow) { +#ifdef CONFIG_XFRM struct xfrm_state *x = pkt_dev->flows[flow].x; struct pktgen_net *pn = net_generic(dev_net(pkt_dev->odev), pg_net_id); if (!x) { @@ -2390,11 +2427,10 @@ static void get_ipsec_sa(struct pktgen_dev *pkt_dev, int flow) } } -} #endif +} static void set_cur_queue_map(struct pktgen_dev *pkt_dev) { - if (pkt_dev->flags & F_QUEUE_MAP_CPU) pkt_dev->cur_queue_map = smp_processor_id(); @@ -2569,10 +2605,8 @@ static void mod_cur_headers(struct pktgen_dev *pkt_dev) pkt_dev->flows[flow].flags |= F_INIT; pkt_dev->flows[flow].cur_daddr = pkt_dev->cur_daddr; -#ifdef CONFIG_XFRM if (pkt_dev->flags & F_IPSEC) get_ipsec_sa(pkt_dev, flow); -#endif pkt_dev->nflows++; } } diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 1f4d4b5570ab..c23852835050 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -53,6 +53,7 @@ #include <net/fib_rules.h> #include <net/rtnetlink.h> #include <net/net_namespace.h> +#include <net/netdev_lock.h> #include <net/devlink.h> #if IS_ENABLED(CONFIG_IPV6) #include <net/addrconf.h> @@ -80,6 +81,11 @@ void rtnl_lock(void) } EXPORT_SYMBOL(rtnl_lock); +int rtnl_lock_interruptible(void) +{ + return mutex_lock_interruptible(&rtnl_mutex); +} + int rtnl_lock_killable(void) { return mutex_lock_killable(&rtnl_mutex); @@ -1171,6 +1177,9 @@ static inline int rtnl_vfinfo_size(const struct net_device *dev, /* IFLA_VF_STATS_TX_DROPPED */ nla_total_size_64bit(sizeof(__u64))); } + if (dev->netdev_ops->ndo_get_vf_guid) + size += num_vfs * 2 * + nla_total_size(sizeof(struct ifla_vf_guid)); return size; } else return 0; @@ -1287,6 +1296,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev, + nla_total_size(4) /* IFLA_TSO_MAX_SEGS */ + nla_total_size(1) /* IFLA_OPERSTATE */ + nla_total_size(1) /* IFLA_LINKMODE */ + + nla_total_size(1) /* IFLA_NETNS_IMMUTABLE */ + nla_total_size(4) /* IFLA_CARRIER_CHANGES */ + nla_total_size(4) /* IFLA_LINK_NETNSID */ + nla_total_size(4) /* IFLA_GROUP */ @@ -2041,6 +2051,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, netif_running(dev) ? READ_ONCE(dev->operstate) : IF_OPER_DOWN) || nla_put_u8(skb, IFLA_LINKMODE, READ_ONCE(dev->link_mode)) || + nla_put_u8(skb, IFLA_NETNS_IMMUTABLE, dev->netns_immutable) || nla_put_u32(skb, IFLA_MTU, READ_ONCE(dev->mtu)) || nla_put_u32(skb, IFLA_MIN_MTU, READ_ONCE(dev->min_mtu)) || nla_put_u32(skb, IFLA_MAX_MTU, READ_ONCE(dev->max_mtu)) || @@ -2229,6 +2240,7 @@ static const struct nla_policy ifla_policy[IFLA_MAX+1] = { [IFLA_ALLMULTI] = { .type = NLA_REJECT }, [IFLA_GSO_IPV4_MAX_SIZE] = NLA_POLICY_MIN(NLA_U32, MAX_TCP_HEADER + 1), [IFLA_GRO_IPV4_MAX_SIZE] = { .type = NLA_U32 }, + [IFLA_NETNS_IMMUTABLE] = { .type = NLA_REJECT }, }; static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = { @@ -2904,12 +2916,19 @@ static int do_set_master(struct net_device *dev, int ifindex, const struct net_device_ops *ops; int err; + /* Release the lower lock, the upper is responsible for locking + * the lower if needed. None of the existing upper devices + * use netdev instance lock, so don't grab it. + */ + if (upper_dev) { if (upper_dev->ifindex == ifindex) return 0; ops = upper_dev->netdev_ops; if (ops->ndo_del_slave) { + netdev_unlock_ops(dev); err = ops->ndo_del_slave(upper_dev, dev); + netdev_lock_ops(dev); if (err) return err; } else { @@ -2923,7 +2942,9 @@ static int do_set_master(struct net_device *dev, int ifindex, return -EINVAL; ops = upper_dev->netdev_ops; if (ops->ndo_add_slave) { + netdev_unlock_ops(dev); err = ops->ndo_add_slave(upper_dev, dev, extack); + netdev_lock_ops(dev); if (err) return err; } else { @@ -2973,7 +2994,7 @@ static int do_set_proto_down(struct net_device *dev, if (pdreason[IFLA_PROTO_DOWN_REASON_MASK]) mask = nla_get_u32(pdreason[IFLA_PROTO_DOWN_REASON_MASK]); - dev_change_proto_down_reason(dev, mask, value); + netdev_change_proto_down_reason_locked(dev, mask, value); } if (nl_proto_down) { @@ -2984,8 +3005,7 @@ static int do_set_proto_down(struct net_device *dev, NL_SET_ERR_MSG(extack, "Cannot clear protodown, active reasons"); return -EBUSY; } - err = dev_change_proto_down(dev, - proto_down); + err = netif_change_proto_down(dev, proto_down); if (err) return err; } @@ -3020,13 +3040,16 @@ static int do_setlink(const struct sk_buff *skb, struct net_device *dev, new_ifindex = nla_get_s32_default(tb[IFLA_NEW_IFINDEX], 0); - err = __dev_change_net_namespace(dev, tgt_net, pat, new_ifindex); + err = __dev_change_net_namespace(dev, tgt_net, pat, + new_ifindex, extack); if (err) - goto errout; + return err; status |= DO_SETLINK_MODIFIED; } + netdev_lock_ops(dev); + if (tb[IFLA_MAP]) { struct rtnl_link_ifmap *u_map; struct ifmap k_map; @@ -3068,24 +3091,35 @@ static int do_setlink(const struct sk_buff *skb, struct net_device *dev, goto errout; } sa->sa_family = dev->type; + + netdev_unlock_ops(dev); + + /* dev_addr_sem is an outer lock, enforce proper ordering */ + down_write(&dev_addr_sem); + netdev_lock_ops(dev); + memcpy(sa->sa_data, nla_data(tb[IFLA_ADDRESS]), dev->addr_len); - err = dev_set_mac_address_user(dev, sa, extack); + err = netif_set_mac_address(dev, sa, extack); kfree(sa); - if (err) + if (err) { + up_write(&dev_addr_sem); goto errout; + } status |= DO_SETLINK_MODIFIED; + + up_write(&dev_addr_sem); } if (tb[IFLA_MTU]) { - err = dev_set_mtu_ext(dev, nla_get_u32(tb[IFLA_MTU]), extack); + err = netif_set_mtu_ext(dev, nla_get_u32(tb[IFLA_MTU]), extack); if (err < 0) goto errout; status |= DO_SETLINK_MODIFIED; } if (tb[IFLA_GROUP]) { - dev_set_group(dev, nla_get_u32(tb[IFLA_GROUP])); + netif_set_group(dev, nla_get_u32(tb[IFLA_GROUP])); status |= DO_SETLINK_NOTIFY; } @@ -3095,15 +3129,15 @@ static int do_setlink(const struct sk_buff *skb, struct net_device *dev, * requested. */ if (ifm->ifi_index > 0 && ifname[0]) { - err = dev_change_name(dev, ifname); + err = netif_change_name(dev, ifname); if (err < 0) goto errout; status |= DO_SETLINK_MODIFIED; } if (tb[IFLA_IFALIAS]) { - err = dev_set_alias(dev, nla_data(tb[IFLA_IFALIAS]), - nla_len(tb[IFLA_IFALIAS])); + err = netif_set_alias(dev, nla_data(tb[IFLA_IFALIAS]), + nla_len(tb[IFLA_IFALIAS])); if (err < 0) goto errout; status |= DO_SETLINK_NOTIFY; @@ -3115,8 +3149,8 @@ static int do_setlink(const struct sk_buff *skb, struct net_device *dev, } if (ifm->ifi_flags || ifm->ifi_change) { - err = dev_change_flags(dev, rtnl_dev_combine_flags(dev, ifm), - extack); + err = netif_change_flags(dev, rtnl_dev_combine_flags(dev, ifm), + extack); if (err < 0) goto errout; } @@ -3129,7 +3163,7 @@ static int do_setlink(const struct sk_buff *skb, struct net_device *dev, } if (tb[IFLA_CARRIER]) { - err = dev_change_carrier(dev, nla_get_u8(tb[IFLA_CARRIER])); + err = netif_change_carrier(dev, nla_get_u8(tb[IFLA_CARRIER])); if (err) goto errout; status |= DO_SETLINK_MODIFIED; @@ -3138,7 +3172,7 @@ static int do_setlink(const struct sk_buff *skb, struct net_device *dev, if (tb[IFLA_TXQLEN]) { unsigned int value = nla_get_u32(tb[IFLA_TXQLEN]); - err = dev_change_tx_queue_len(dev, value); + err = netif_change_tx_queue_len(dev, value); if (err) goto errout; status |= DO_SETLINK_MODIFIED; @@ -3369,6 +3403,8 @@ errout: dev->name); } + netdev_unlock_ops(dev); + return err; } @@ -3432,6 +3468,7 @@ static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh, err = -ENODEV; rtnl_nets_unlock(&rtnl_nets); + rtnl_nets_destroy(&rtnl_nets); errout: return err; } @@ -3761,7 +3798,13 @@ static int rtnl_newlink_create(struct sk_buff *skb, struct ifinfomsg *ifm, struct netlink_ext_ack *extack) { unsigned char name_assign_type = NET_NAME_USER; - struct net *net = sock_net(skb->sk); + struct rtnl_newlink_params params = { + .src_net = sock_net(skb->sk), + .link_net = link_net, + .peer_net = peer_net, + .tb = tb, + .data = data, + }; u32 portid = NETLINK_CB(skb).portid; struct net_device *dev; char ifname[IFNAMSIZ]; @@ -3777,8 +3820,8 @@ static int rtnl_newlink_create(struct sk_buff *skb, struct ifinfomsg *ifm, name_assign_type = NET_NAME_ENUM; } - dev = rtnl_create_link(link_net ? : tgt_net, ifname, - name_assign_type, ops, tb, extack); + dev = rtnl_create_link(tgt_net, ifname, name_assign_type, ops, tb, + extack); if (IS_ERR(dev)) { err = PTR_ERR(dev); goto out; @@ -3786,13 +3829,8 @@ static int rtnl_newlink_create(struct sk_buff *skb, struct ifinfomsg *ifm, dev->ifindex = ifm->ifi_index; - if (link_net) - net = link_net; - if (peer_net) - net = peer_net; - if (ops->newlink) - err = ops->newlink(net, dev, tb, data, extack); + err = ops->newlink(dev, ¶ms, extack); else err = register_netdevice(dev); if (err < 0) { @@ -3800,22 +3838,22 @@ static int rtnl_newlink_create(struct sk_buff *skb, struct ifinfomsg *ifm, goto out; } + netdev_lock_ops(dev); + err = rtnl_configure_link(dev, ifm, portid, nlh); if (err < 0) goto out_unregister; - if (link_net) { - err = dev_change_net_namespace(dev, tgt_net, ifname); - if (err < 0) - goto out_unregister; - } if (tb[IFLA_MASTER]) { err = do_set_master(dev, nla_get_u32(tb[IFLA_MASTER]), extack); if (err) goto out_unregister; } + + netdev_unlock_ops(dev); out: return err; out_unregister: + netdev_unlock_ops(dev); if (ops->newlink) { LIST_HEAD(list_kill); @@ -3861,20 +3899,26 @@ static int __rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh, { struct nlattr ** const tb = tbs->tb; struct net *net = sock_net(skb->sk); + struct net *device_net; struct net_device *dev; struct ifinfomsg *ifm; bool link_specified; + /* When creating, lookup for existing device in target net namespace */ + device_net = (nlh->nlmsg_flags & NLM_F_CREATE) && + (nlh->nlmsg_flags & NLM_F_EXCL) ? + tgt_net : net; + ifm = nlmsg_data(nlh); if (ifm->ifi_index > 0) { link_specified = true; - dev = __dev_get_by_index(net, ifm->ifi_index); + dev = __dev_get_by_index(device_net, ifm->ifi_index); } else if (ifm->ifi_index < 0) { NL_SET_ERR_MSG(extack, "ifindex can't be negative"); return -EINVAL; } else if (tb[IFLA_IFNAME] || tb[IFLA_ALT_IFNAME]) { link_specified = true; - dev = rtnl_dev_get(net, tb); + dev = rtnl_dev_get(device_net, tb); } else { link_specified = false; dev = NULL; diff --git a/net/core/scm.c b/net/core/scm.c index 4f6a14babe5a..733c0cbd393d 100644 --- a/net/core/scm.c +++ b/net/core/scm.c @@ -282,6 +282,16 @@ efault: } EXPORT_SYMBOL(put_cmsg); +int put_cmsg_notrunc(struct msghdr *msg, int level, int type, int len, + void *data) +{ + /* Don't produce truncated CMSGs */ + if (!msg->msg_control || msg->msg_controllen < CMSG_LEN(len)) + return -ETOOSMALL; + + return put_cmsg(msg, level, type, len, data); +} + void put_cmsg_scm_timestamping64(struct msghdr *msg, struct scm_timestamping_internal *tss_internal) { struct scm_timestamping64 tss; diff --git a/net/core/secure_seq.c b/net/core/secure_seq.c index b0ff6153be62..568779d5a0ef 100644 --- a/net/core/secure_seq.c +++ b/net/core/secure_seq.c @@ -71,7 +71,7 @@ u32 secure_tcpv6_ts_off(const struct net *net, return siphash(&combined, offsetofend(typeof(combined), daddr), &ts_secret); } -EXPORT_SYMBOL(secure_tcpv6_ts_off); +EXPORT_IPV6_MOD(secure_tcpv6_ts_off); u32 secure_tcpv6_seq(const __be32 *saddr, const __be32 *daddr, __be16 sport, __be16 dport) diff --git a/net/core/selftests.c b/net/core/selftests.c index 8f801e6e3b91..e99ae983fca9 100644 --- a/net/core/selftests.c +++ b/net/core/selftests.c @@ -299,7 +299,7 @@ static int net_test_phy_loopback_enable(struct net_device *ndev) if (!ndev->phydev) return -EOPNOTSUPP; - return phy_loopback(ndev->phydev, true); + return phy_loopback(ndev->phydev, true, 0); } static int net_test_phy_loopback_disable(struct net_device *ndev) @@ -307,7 +307,7 @@ static int net_test_phy_loopback_disable(struct net_device *ndev) if (!ndev->phydev) return -EOPNOTSUPP; - return phy_loopback(ndev->phydev, false); + return phy_loopback(ndev->phydev, false, 0); } static int net_test_phy_loopback_udp(struct net_device *ndev) diff --git a/net/core/skbuff.c b/net/core/skbuff.c index a441613a1e6c..6cbf77bc61fc 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -69,6 +69,7 @@ #include <net/dst.h> #include <net/sock.h> #include <net/checksum.h> +#include <net/gro.h> #include <net/gso.h> #include <net/hotdata.h> #include <net/ip6_checksum.h> @@ -95,7 +96,9 @@ static struct kmem_cache *skbuff_ext_cache __ro_after_init; #endif -#define SKB_SMALL_HEAD_SIZE SKB_HEAD_ALIGN(MAX_TCP_HEADER) +#define GRO_MAX_HEAD_PAD (GRO_MAX_HEAD + NET_SKB_PAD + NET_IP_ALIGN) +#define SKB_SMALL_HEAD_SIZE SKB_HEAD_ALIGN(max(MAX_TCP_HEADER, \ + GRO_MAX_HEAD_PAD)) /* We want SKB_SMALL_HEAD_CACHE_SIZE to not be a power of two. * This should ensure that SKB_SMALL_HEAD_HEADROOM is a unique @@ -220,67 +223,9 @@ static void skb_under_panic(struct sk_buff *skb, unsigned int sz, void *addr) #define NAPI_SKB_CACHE_BULK 16 #define NAPI_SKB_CACHE_HALF (NAPI_SKB_CACHE_SIZE / 2) -#if PAGE_SIZE == SZ_4K - -#define NAPI_HAS_SMALL_PAGE_FRAG 1 -#define NAPI_SMALL_PAGE_PFMEMALLOC(nc) ((nc).pfmemalloc) - -/* specialized page frag allocator using a single order 0 page - * and slicing it into 1K sized fragment. Constrained to systems - * with a very limited amount of 1K fragments fitting a single - * page - to avoid excessive truesize underestimation - */ - -struct page_frag_1k { - void *va; - u16 offset; - bool pfmemalloc; -}; - -static void *page_frag_alloc_1k(struct page_frag_1k *nc, gfp_t gfp) -{ - struct page *page; - int offset; - - offset = nc->offset - SZ_1K; - if (likely(offset >= 0)) - goto use_frag; - - page = alloc_pages_node(NUMA_NO_NODE, gfp, 0); - if (!page) - return NULL; - - nc->va = page_address(page); - nc->pfmemalloc = page_is_pfmemalloc(page); - offset = PAGE_SIZE - SZ_1K; - page_ref_add(page, offset / SZ_1K); - -use_frag: - nc->offset = offset; - return nc->va + offset; -} -#else - -/* the small page is actually unused in this build; add dummy helpers - * to please the compiler and avoid later preprocessor's conditionals - */ -#define NAPI_HAS_SMALL_PAGE_FRAG 0 -#define NAPI_SMALL_PAGE_PFMEMALLOC(nc) false - -struct page_frag_1k { -}; - -static void *page_frag_alloc_1k(struct page_frag_1k *nc, gfp_t gfp_mask) -{ - return NULL; -} - -#endif - struct napi_alloc_cache { local_lock_t bh_lock; struct page_frag_cache page; - struct page_frag_1k page_small; unsigned int skb_count; void *skb_cache[NAPI_SKB_CACHE_SIZE]; }; @@ -290,23 +235,6 @@ static DEFINE_PER_CPU(struct napi_alloc_cache, napi_alloc_cache) = { .bh_lock = INIT_LOCAL_LOCK(bh_lock), }; -/* Double check that napi_get_frags() allocates skbs with - * skb->head being backed by slab, not a page fragment. - * This is to make sure bug fixed in 3226b158e67c - * ("net: avoid 32 x truesize under-estimation for tiny skbs") - * does not accidentally come back. - */ -void napi_get_frags_check(struct napi_struct *napi) -{ - struct sk_buff *skb; - - local_bh_disable(); - skb = napi_get_frags(napi); - WARN_ON_ONCE(!NAPI_HAS_SMALL_PAGE_FRAG && skb && skb->head_frag); - napi_free_frags(napi); - local_bh_enable(); -} - void *__napi_alloc_frag_align(unsigned int fragsz, unsigned int align_mask) { struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache); @@ -367,6 +295,68 @@ static struct sk_buff *napi_skb_cache_get(void) return skb; } +/** + * napi_skb_cache_get_bulk - obtain a number of zeroed skb heads from the cache + * @skbs: pointer to an at least @n-sized array to fill with skb pointers + * @n: number of entries to provide + * + * Tries to obtain @n &sk_buff entries from the NAPI percpu cache and writes + * the pointers into the provided array @skbs. If there are less entries + * available, tries to replenish the cache and bulk-allocates the diff from + * the MM layer if needed. + * The heads are being zeroed with either memset() or %__GFP_ZERO, so they are + * ready for {,__}build_skb_around() and don't have any data buffers attached. + * Must be called *only* from the BH context. + * + * Return: number of successfully allocated skbs (@n if no actual allocation + * needed or kmem_cache_alloc_bulk() didn't fail). + */ +u32 napi_skb_cache_get_bulk(void **skbs, u32 n) +{ + struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache); + u32 bulk, total = n; + + local_lock_nested_bh(&napi_alloc_cache.bh_lock); + + if (nc->skb_count >= n) + goto get; + + /* No enough cached skbs. Try refilling the cache first */ + bulk = min(NAPI_SKB_CACHE_SIZE - nc->skb_count, NAPI_SKB_CACHE_BULK); + nc->skb_count += kmem_cache_alloc_bulk(net_hotdata.skbuff_cache, + GFP_ATOMIC | __GFP_NOWARN, bulk, + &nc->skb_cache[nc->skb_count]); + if (likely(nc->skb_count >= n)) + goto get; + + /* Still not enough. Bulk-allocate the missing part directly, zeroed */ + n -= kmem_cache_alloc_bulk(net_hotdata.skbuff_cache, + GFP_ATOMIC | __GFP_ZERO | __GFP_NOWARN, + n - nc->skb_count, &skbs[nc->skb_count]); + if (likely(nc->skb_count >= n)) + goto get; + + /* kmem_cache didn't allocate the number we need, limit the output */ + total -= n - nc->skb_count; + n = nc->skb_count; + +get: + for (u32 base = nc->skb_count - n, i = 0; i < n; i++) { + u32 cache_size = kmem_cache_size(net_hotdata.skbuff_cache); + + skbs[i] = nc->skb_cache[base + i]; + + kasan_mempool_unpoison_object(skbs[i], cache_size); + memset(skbs[i], 0, offsetof(struct sk_buff, tail)); + } + + nc->skb_count -= n; + local_unlock_nested_bh(&napi_alloc_cache.bh_lock); + + return total; +} +EXPORT_SYMBOL_GPL(napi_skb_cache_get_bulk); + static inline void __finalize_skb_around(struct sk_buff *skb, void *data, unsigned int size) { @@ -736,7 +726,7 @@ struct sk_buff *__netdev_alloc_skb(struct net_device *dev, unsigned int len, /* If requested length is either too small or too big, * we use kmalloc() for skb->head allocation. */ - if (len <= SKB_WITH_OVERHEAD(1024) || + if (len <= SKB_WITH_OVERHEAD(SKB_SMALL_HEAD_CACHE_SIZE) || len > SKB_WITH_OVERHEAD(PAGE_SIZE) || (gfp_mask & (__GFP_DIRECT_RECLAIM | GFP_DMA))) { skb = __alloc_skb(len, gfp_mask, SKB_ALLOC_RX, NUMA_NO_NODE); @@ -813,10 +803,8 @@ struct sk_buff *napi_alloc_skb(struct napi_struct *napi, unsigned int len) /* If requested length is either too small or too big, * we use kmalloc() for skb->head allocation. - * When the small frag allocator is available, prefer it over kmalloc - * for small fragments */ - if ((!NAPI_HAS_SMALL_PAGE_FRAG && len <= SKB_WITH_OVERHEAD(1024)) || + if (len <= SKB_WITH_OVERHEAD(SKB_SMALL_HEAD_CACHE_SIZE) || len > SKB_WITH_OVERHEAD(PAGE_SIZE) || (gfp_mask & (__GFP_DIRECT_RECLAIM | GFP_DMA))) { skb = __alloc_skb(len, gfp_mask, SKB_ALLOC_RX | SKB_ALLOC_NAPI, @@ -826,32 +814,16 @@ struct sk_buff *napi_alloc_skb(struct napi_struct *napi, unsigned int len) goto skb_success; } + len = SKB_HEAD_ALIGN(len); + if (sk_memalloc_socks()) gfp_mask |= __GFP_MEMALLOC; local_lock_nested_bh(&napi_alloc_cache.bh_lock); nc = this_cpu_ptr(&napi_alloc_cache); - if (NAPI_HAS_SMALL_PAGE_FRAG && len <= SKB_WITH_OVERHEAD(1024)) { - /* we are artificially inflating the allocation size, but - * that is not as bad as it may look like, as: - * - 'len' less than GRO_MAX_HEAD makes little sense - * - On most systems, larger 'len' values lead to fragment - * size above 512 bytes - * - kmalloc would use the kmalloc-1k slab for such values - * - Builds with smaller GRO_MAX_HEAD will very likely do - * little networking, as that implies no WiFi and no - * tunnels support, and 32 bits arches. - */ - len = SZ_1K; - - data = page_frag_alloc_1k(&nc->page_small, gfp_mask); - pfmemalloc = NAPI_SMALL_PAGE_PFMEMALLOC(nc->page_small); - } else { - len = SKB_HEAD_ALIGN(len); - data = page_frag_alloc(&nc->page, len, gfp_mask); - pfmemalloc = page_frag_cache_is_pfmemalloc(&nc->page); - } + data = page_frag_alloc(&nc->page, len, gfp_mask); + pfmemalloc = page_frag_cache_is_pfmemalloc(&nc->page); local_unlock_nested_bh(&napi_alloc_cache.bh_lock); if (unlikely(!data)) @@ -5539,6 +5511,54 @@ err: } EXPORT_SYMBOL_GPL(skb_complete_tx_timestamp); +static bool skb_tstamp_tx_report_so_timestamping(struct sk_buff *skb, + struct skb_shared_hwtstamps *hwtstamps, + int tstype) +{ + switch (tstype) { + case SCM_TSTAMP_SCHED: + return skb_shinfo(skb)->tx_flags & SKBTX_SCHED_TSTAMP; + case SCM_TSTAMP_SND: + return skb_shinfo(skb)->tx_flags & (hwtstamps ? SKBTX_HW_TSTAMP_NOBPF : + SKBTX_SW_TSTAMP); + case SCM_TSTAMP_ACK: + return TCP_SKB_CB(skb)->txstamp_ack & TSTAMP_ACK_SK; + case SCM_TSTAMP_COMPLETION: + return skb_shinfo(skb)->tx_flags & SKBTX_COMPLETION_TSTAMP; + } + + return false; +} + +static void skb_tstamp_tx_report_bpf_timestamping(struct sk_buff *skb, + struct skb_shared_hwtstamps *hwtstamps, + struct sock *sk, + int tstype) +{ + int op; + + switch (tstype) { + case SCM_TSTAMP_SCHED: + op = BPF_SOCK_OPS_TSTAMP_SCHED_CB; + break; + case SCM_TSTAMP_SND: + if (hwtstamps) { + op = BPF_SOCK_OPS_TSTAMP_SND_HW_CB; + *skb_hwtstamps(skb) = *hwtstamps; + } else { + op = BPF_SOCK_OPS_TSTAMP_SND_SW_CB; + } + break; + case SCM_TSTAMP_ACK: + op = BPF_SOCK_OPS_TSTAMP_ACK_CB; + break; + default: + return; + } + + bpf_skops_tx_timestamping(sk, skb, op); +} + void __skb_tstamp_tx(struct sk_buff *orig_skb, const struct sk_buff *ack_skb, struct skb_shared_hwtstamps *hwtstamps, @@ -5551,6 +5571,13 @@ void __skb_tstamp_tx(struct sk_buff *orig_skb, if (!sk) return; + if (skb_shinfo(orig_skb)->tx_flags & SKBTX_BPF) + skb_tstamp_tx_report_bpf_timestamping(orig_skb, hwtstamps, + sk, tstype); + + if (!skb_tstamp_tx_report_so_timestamping(orig_skb, hwtstamps, tstype)) + return; + tsflags = READ_ONCE(sk->sk_tsflags); if (!hwtstamps && !(tsflags & SOF_TIMESTAMPING_OPT_TX_SWHW) && skb_shinfo(orig_skb)->tx_flags & SKBTX_IN_PROGRESS) @@ -6123,11 +6150,11 @@ void skb_scrub_packet(struct sk_buff *skb, bool xnet) skb->offload_fwd_mark = 0; skb->offload_l3_fwd_mark = 0; #endif + ipvs_reset(skb); if (!xnet) return; - ipvs_reset(skb); skb->mark = 0; skb_clear_tstamp(skb); } diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 61f3f3d4e528..0ddc4c718833 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -549,6 +549,9 @@ static int sk_psock_skb_ingress_enqueue(struct sk_buff *skb, return num_sge; } +#if IS_ENABLED(CONFIG_BPF_STREAM_PARSER) + psock->ingress_bytes += len; +#endif copied = len; msg->sg.start = 0; msg->sg.size = copied; @@ -1144,6 +1147,10 @@ int sk_psock_init_strp(struct sock *sk, struct sk_psock *psock) if (!ret) sk_psock_set_state(psock, SK_PSOCK_RX_STRP_ENABLED); + if (sk_is_tcp(sk)) { + psock->strp.cb.read_sock = tcp_bpf_strp_read_sock; + psock->copied_seq = tcp_sk(sk)->copied_seq; + } return ret; } diff --git a/net/core/sock.c b/net/core/sock.c index eae2ae70a2e0..f67a3c5b0988 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -938,6 +938,7 @@ int sock_set_timestamping(struct sock *sk, int optname, WRITE_ONCE(sk->sk_tsflags, val); sock_valbool_flag(sk, SOCK_TSTAMP_NEW, optname == SO_TIMESTAMPING_NEW); + sock_valbool_flag(sk, SOCK_TIMESTAMPING_ANY, !!(val & TSFLAGS_ANY)); if (val & SOF_TIMESTAMPING_RX_SOFTWARE) sock_enable_timestamp(sk, @@ -948,6 +949,20 @@ int sock_set_timestamping(struct sock *sk, int optname, return 0; } +#if defined(CONFIG_CGROUP_BPF) +void bpf_skops_tx_timestamping(struct sock *sk, struct sk_buff *skb, int op) +{ + struct bpf_sock_ops_kern sock_ops; + + memset(&sock_ops, 0, offsetof(struct bpf_sock_ops_kern, temp)); + sock_ops.op = op; + sock_ops.is_fullsock = 1; + sock_ops.sk = sk; + bpf_skops_init_skb(&sock_ops, skb, 0); + __cgroup_bpf_run_filter_sock_ops(sk, &sock_ops, CGROUP_SOCK_OPS); +} +#endif + void sock_set_keepalive(struct sock *sk) { lock_sock(sk); @@ -2041,7 +2056,7 @@ int sk_getsockopt(struct sock *sk, int level, int optname, v.val = READ_ONCE(sk->sk_napi_id); /* aggregate non-NAPI IDs down to 0 */ - if (v.val < MIN_NAPI_ID) + if (!napi_id_valid(v.val)) v.val = 0; break; @@ -2246,6 +2261,7 @@ struct sock *sk_alloc(struct net *net, int family, gfp_t priority, get_net_track(net, &sk->ns_tracker, priority); sock_inuse_add(net, 1); } else { + net_passive_inc(net); __netns_tracker_alloc(net, &sk->ns_tracker, false, priority); } @@ -2270,6 +2286,7 @@ EXPORT_SYMBOL(sk_alloc); static void __sk_destruct(struct rcu_head *head) { struct sock *sk = container_of(head, struct sock, sk_rcu); + struct net *net = sock_net(sk); struct sk_filter *filter; if (sk->sk_destruct) @@ -2301,14 +2318,28 @@ static void __sk_destruct(struct rcu_head *head) put_cred(sk->sk_peer_cred); put_pid(sk->sk_peer_pid); - if (likely(sk->sk_net_refcnt)) - put_net_track(sock_net(sk), &sk->ns_tracker); - else - __netns_tracker_free(sock_net(sk), &sk->ns_tracker, false); - + if (likely(sk->sk_net_refcnt)) { + put_net_track(net, &sk->ns_tracker); + } else { + __netns_tracker_free(net, &sk->ns_tracker, false); + net_passive_dec(net); + } sk_prot_free(sk->sk_prot_creator, sk); } +void sk_net_refcnt_upgrade(struct sock *sk) +{ + struct net *net = sock_net(sk); + + WARN_ON_ONCE(sk->sk_net_refcnt); + __netns_tracker_free(net, &sk->ns_tracker, false); + net_passive_dec(net); + sk->sk_net_refcnt = 1; + get_net_track(net, &sk->ns_tracker, GFP_KERNEL); + sock_inuse_add(net, 1); +} +EXPORT_SYMBOL_GPL(sk_net_refcnt_upgrade); + void sk_destruct(struct sock *sk) { bool use_call_rcu = sock_flag(sk, SOCK_RCU_FREE); @@ -2405,6 +2436,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) * is not properly dismantling its kernel sockets at netns * destroy time. */ + net_passive_inc(sock_net(newsk)); __netns_tracker_alloc(sock_net(newsk), &newsk->ns_tracker, false, priority); } @@ -2533,8 +2565,12 @@ void sk_setup_caps(struct sock *sk, struct dst_entry *dst) u32 max_segs = 1; sk->sk_route_caps = dst->dev->features; - if (sk_is_tcp(sk)) + if (sk_is_tcp(sk)) { + struct inet_connection_sock *icsk = inet_csk(sk); + sk->sk_route_caps |= NETIF_F_GSO; + icsk->icsk_ack.dst_quick_ack = dst_metric(dst, RTAX_QUICKACK); + } if (sk->sk_route_caps & NETIF_F_GSO) sk->sk_route_caps |= NETIF_F_GSO_SOFTWARE; if (unlikely(sk->sk_gso_disabled)) @@ -2804,6 +2840,22 @@ void *sock_kmalloc(struct sock *sk, int size, gfp_t priority) } EXPORT_SYMBOL(sock_kmalloc); +/* + * Duplicate the input "src" memory block using the socket's + * option memory buffer. + */ +void *sock_kmemdup(struct sock *sk, const void *src, + int size, gfp_t priority) +{ + void *mem; + + mem = sock_kmalloc(sk, size, priority); + if (mem) + memcpy(mem, src, size); + return mem; +} +EXPORT_SYMBOL(sock_kmemdup); + /* Free an option memory block. Note, we actually want the inline * here as this allows gcc to detect the nullify and fold away the * condition entirely. @@ -3546,14 +3598,14 @@ EXPORT_SYMBOL(sk_reset_timer); void sk_stop_timer(struct sock *sk, struct timer_list* timer) { - if (del_timer(timer)) + if (timer_delete(timer)) __sock_put(sk); } EXPORT_SYMBOL(sk_stop_timer); void sk_stop_timer_sync(struct sock *sk, struct timer_list *timer) { - if (del_timer_sync(timer)) + if (timer_delete_sync(timer)) __sock_put(sk); } EXPORT_SYMBOL(sk_stop_timer_sync); @@ -3881,7 +3933,7 @@ void sk_get_meminfo(const struct sock *sk, u32 *mem) mem[SK_MEMINFO_RCVBUF] = READ_ONCE(sk->sk_rcvbuf); mem[SK_MEMINFO_WMEM_ALLOC] = sk_wmem_alloc_get(sk); mem[SK_MEMINFO_SNDBUF] = READ_ONCE(sk->sk_sndbuf); - mem[SK_MEMINFO_FWD_ALLOC] = sk_forward_alloc_get(sk); + mem[SK_MEMINFO_FWD_ALLOC] = READ_ONCE(sk->sk_forward_alloc); mem[SK_MEMINFO_WMEM_QUEUED] = READ_ONCE(sk->sk_wmem_queued); mem[SK_MEMINFO_OPTMEM] = atomic_read(&sk->sk_omem_alloc); mem[SK_MEMINFO_BACKLOG] = READ_ONCE(sk->sk_backlog.len); diff --git a/net/core/sock_map.c b/net/core/sock_map.c index f1b9b3958792..82a14f131d00 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -303,7 +303,10 @@ static int sock_map_link(struct bpf_map *map, struct sock *sk) write_lock_bh(&sk->sk_callback_lock); if (stream_parser && stream_verdict && !psock->saved_data_ready) { - ret = sk_psock_init_strp(sk, psock); + if (sk_is_tcp(sk)) + ret = sk_psock_init_strp(sk, psock); + else + ret = -EOPNOTSUPP; if (ret) { write_unlock_bh(&sk->sk_callback_lock); sk_psock_put(sk, psock); @@ -541,6 +544,9 @@ static bool sock_map_sk_state_allowed(const struct sock *sk) return (1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_LISTEN); if (sk_is_stream_unix(sk)) return (1 << sk->sk_state) & TCPF_ESTABLISHED; + if (sk_is_vsock(sk) && + (sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET)) + return (1 << sk->sk_state) & TCPF_ESTABLISHED; return true; } diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index ad2741f1346a..c7769ee0d9c5 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -34,6 +34,7 @@ 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 netdev_budget_usecs_min = 2 * USEC_PER_SEC / HZ; static int net_msg_warn; /* Unused, but still a sysctl */ @@ -587,7 +588,7 @@ static struct ctl_table net_core_table[] = { .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ZERO, + .extra1 = &netdev_budget_usecs_min, }, { .procname = "fb_tunnels_only_for_init_net", diff --git a/net/core/xdp.c b/net/core/xdp.c index 2c6ab6fb452f..f86eedad586a 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -618,16 +618,6 @@ void xdp_warn(const char *msg, const char *func, const int line) }; EXPORT_SYMBOL_GPL(xdp_warn); -int xdp_alloc_skb_bulk(void **skbs, int n_skb, gfp_t gfp) -{ - n_skb = kmem_cache_alloc_bulk(net_hotdata.skbuff_cache, gfp, n_skb, skbs); - if (unlikely(!n_skb)) - return -ENOMEM; - - return 0; -} -EXPORT_SYMBOL_GPL(xdp_alloc_skb_bulk); - /** * xdp_build_skb_from_buff - create an skb from &xdp_buff * @xdp: &xdp_buff to convert to an skb |