diff options
Diffstat (limited to 'net/core/dev.c')
| -rw-r--r-- | net/core/dev.c | 1742 |
1 files changed, 736 insertions, 1006 deletions
diff --git a/net/core/dev.c b/net/core/dev.c index 2a352e668d10..3be256051e99 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -151,18 +151,13 @@ #include <linux/prandom.h> #include <linux/once_lite.h> +#include "dev.h" #include "net-sysfs.h" -#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(ptype_lock); -static DEFINE_SPINLOCK(offload_lock); struct list_head ptype_base[PTYPE_HASH_SIZE] __read_mostly; struct list_head ptype_all __read_mostly; /* Taps */ -static struct list_head offload_base __read_mostly; static int netif_rx_internal(struct sk_buff *skb); static int call_netdevice_notifiers_info(unsigned long val, @@ -222,18 +217,38 @@ static inline struct hlist_head *dev_index_hash(struct net *net, int ifindex) return &net->dev_index_head[ifindex & (NETDEV_HASHENTRIES - 1)]; } -static inline void rps_lock(struct softnet_data *sd) +static inline void rps_lock_irqsave(struct softnet_data *sd, + unsigned long *flags) { -#ifdef CONFIG_RPS - spin_lock(&sd->input_pkt_queue.lock); -#endif + if (IS_ENABLED(CONFIG_RPS)) + spin_lock_irqsave(&sd->input_pkt_queue.lock, *flags); + else if (!IS_ENABLED(CONFIG_PREEMPT_RT)) + local_irq_save(*flags); } -static inline void rps_unlock(struct softnet_data *sd) +static inline void rps_lock_irq_disable(struct softnet_data *sd) { -#ifdef CONFIG_RPS - spin_unlock(&sd->input_pkt_queue.lock); -#endif + if (IS_ENABLED(CONFIG_RPS)) + spin_lock_irq(&sd->input_pkt_queue.lock); + else if (!IS_ENABLED(CONFIG_PREEMPT_RT)) + local_irq_disable(); +} + +static inline void rps_unlock_irq_restore(struct softnet_data *sd, + unsigned long *flags) +{ + if (IS_ENABLED(CONFIG_RPS)) + spin_unlock_irqrestore(&sd->input_pkt_queue.lock, *flags); + else if (!IS_ENABLED(CONFIG_PREEMPT_RT)) + local_irq_restore(*flags); +} + +static inline void rps_unlock_irq_enable(struct softnet_data *sd) +{ + if (IS_ENABLED(CONFIG_RPS)) + spin_unlock_irq(&sd->input_pkt_queue.lock); + else if (!IS_ENABLED(CONFIG_PREEMPT_RT)) + local_irq_enable(); } static struct netdev_name_node *netdev_name_node_alloc(struct net_device *dev, @@ -326,7 +341,6 @@ int netdev_name_node_alt_create(struct net_device *dev, const char *name) return 0; } -EXPORT_SYMBOL(netdev_name_node_alt_create); static void __netdev_name_node_alt_destroy(struct netdev_name_node *name_node) { @@ -354,7 +368,6 @@ int netdev_name_node_alt_destroy(struct net_device *dev, const char *name) return 0; } -EXPORT_SYMBOL(netdev_name_node_alt_destroy); static void netdev_name_node_alt_flush(struct net_device *dev) { @@ -371,12 +384,12 @@ static void list_netdevice(struct net_device *dev) ASSERT_RTNL(); - write_lock_bh(&dev_base_lock); + write_lock(&dev_base_lock); list_add_tail_rcu(&dev->dev_list, &net->dev_base_head); netdev_name_node_add(net, dev->name_node); hlist_add_head_rcu(&dev->index_hlist, dev_index_hash(net, dev->ifindex)); - write_unlock_bh(&dev_base_lock); + write_unlock(&dev_base_lock); dev_base_seq_inc(net); } @@ -384,16 +397,18 @@ static void list_netdevice(struct net_device *dev) /* Device list removal * caller must respect a RCU grace period before freeing/reusing dev */ -static void unlist_netdevice(struct net_device *dev) +static void unlist_netdevice(struct net_device *dev, bool lock) { ASSERT_RTNL(); /* Unlink dev from the device chain */ - write_lock_bh(&dev_base_lock); + if (lock) + write_lock(&dev_base_lock); list_del_rcu(&dev->dev_list); netdev_name_node_del(dev->name_node); hlist_del_rcu(&dev->index_hlist); - write_unlock_bh(&dev_base_lock); + if (lock) + write_unlock(&dev_base_lock); dev_base_seq_inc(dev_net(dev)); } @@ -604,84 +619,6 @@ void dev_remove_pack(struct packet_type *pt) EXPORT_SYMBOL(dev_remove_pack); -/** - * dev_add_offload - register offload handlers - * @po: protocol offload declaration - * - * Add protocol offload handlers to the networking stack. The passed - * &proto_offload is linked into kernel lists and may not be freed until - * it has been removed from the kernel lists. - * - * This call does not sleep therefore it can not - * guarantee all CPU's that are in middle of receiving packets - * will see the new offload handlers (until the next received packet). - */ -void dev_add_offload(struct packet_offload *po) -{ - struct packet_offload *elem; - - spin_lock(&offload_lock); - list_for_each_entry(elem, &offload_base, list) { - if (po->priority < elem->priority) - break; - } - list_add_rcu(&po->list, elem->list.prev); - spin_unlock(&offload_lock); -} -EXPORT_SYMBOL(dev_add_offload); - -/** - * __dev_remove_offload - remove offload handler - * @po: packet offload declaration - * - * Remove a protocol offload handler that was previously added to the - * kernel offload handlers by dev_add_offload(). The passed &offload_type - * is removed from the kernel lists and can be freed or reused once this - * function returns. - * - * The packet type might still be in use by receivers - * and must not be freed until after all the CPU's have gone - * through a quiescent state. - */ -static void __dev_remove_offload(struct packet_offload *po) -{ - struct list_head *head = &offload_base; - struct packet_offload *po1; - - spin_lock(&offload_lock); - - list_for_each_entry(po1, head, list) { - if (po == po1) { - list_del_rcu(&po->list); - goto out; - } - } - - pr_warn("dev_remove_offload: %p not found\n", po); -out: - spin_unlock(&offload_lock); -} - -/** - * dev_remove_offload - remove packet offload handler - * @po: packet offload declaration - * - * Remove a packet offload handler that was previously added to the kernel - * offload handlers by dev_add_offload(). The passed &offload_type is - * removed from the kernel lists and can be freed or reused once this - * function returns. - * - * This call sleeps to guarantee that no CPU is looking at the packet - * type after return. - */ -void dev_remove_offload(struct packet_offload *po) -{ - __dev_remove_offload(po); - - synchronize_net(); -} -EXPORT_SYMBOL(dev_remove_offload); - /******************************************************************************* * * Device Interface Subroutines @@ -747,11 +684,11 @@ int dev_fill_forward_path(const struct net_device *dev, const u8 *daddr, const struct net_device *last_dev; struct net_device_path_ctx ctx = { .dev = dev, - .daddr = daddr, }; struct net_device_path *path; int ret = 0; + memcpy(ctx.daddr, daddr, sizeof(ctx.daddr)); stack->num_paths = 0; while (ctx.dev && ctx.dev->netdev_ops->ndo_fill_forward_path) { last_dev = ctx.dev; @@ -767,6 +704,10 @@ int dev_fill_forward_path(const struct net_device *dev, const u8 *daddr, if (WARN_ON_ONCE(last_dev == ctx.dev)) return -1; } + + if (!ctx.dev) + return ret; + path = dev_fwd_path(stack); if (!path) return -1; @@ -1121,7 +1062,7 @@ static int __dev_alloc_name(struct net *net, const char *name, char *buf) /* avoid cases where sscanf is not exact inverse of printf */ snprintf(buf, IFNAMSIZ, name, i); if (!strncmp(buf, name_node->name, IFNAMSIZ)) - set_bit(i, inuse); + __set_bit(i, inuse); } if (!sscanf(d->name, name, &i)) continue; @@ -1131,7 +1072,7 @@ static int __dev_alloc_name(struct net *net, const char *name, char *buf) /* avoid cases where sscanf is not exact inverse of printf */ snprintf(buf, IFNAMSIZ, name, i); if (!strncmp(buf, d->name, IFNAMSIZ)) - set_bit(i, inuse); + __set_bit(i, inuse); } i = find_first_zero_bit(inuse, max_netdevices); @@ -1159,7 +1100,7 @@ static int dev_alloc_name_ns(struct net *net, BUG_ON(!net); ret = __dev_alloc_name(net, name, buf); if (ret >= 0) - strlcpy(dev->name, buf, IFNAMSIZ); + strscpy(dev->name, buf, IFNAMSIZ); return ret; } @@ -1196,7 +1137,7 @@ static int dev_get_valid_name(struct net *net, struct net_device *dev, else if (netdev_name_in_use(net, name)) return -EEXIST; else if (dev->name != name) - strlcpy(dev->name, name, IFNAMSIZ); + strscpy(dev->name, name, IFNAMSIZ); return 0; } @@ -1272,15 +1213,15 @@ rollback: netdev_adjacent_rename_links(dev, oldname); - write_lock_bh(&dev_base_lock); + write_lock(&dev_base_lock); netdev_name_node_del(dev->name_node); - write_unlock_bh(&dev_base_lock); + write_unlock(&dev_base_lock); synchronize_rcu(); - write_lock_bh(&dev_base_lock); + write_lock(&dev_base_lock); netdev_name_node_add(net, dev->name_node); - write_unlock_bh(&dev_base_lock); + write_unlock(&dev_base_lock); ret = call_netdevice_notifiers(NETDEV_CHANGENAME, dev); ret = notifier_to_errno(ret); @@ -1461,6 +1402,7 @@ static int __dev_open(struct net_device *dev, struct netlink_ext_ack *extack) int ret; ASSERT_RTNL(); + dev_addr_check(dev); if (!netif_device_present(dev)) { /* may be detached because parent is runtime-suspended */ @@ -1685,7 +1627,8 @@ const char *netdev_cmd_to_name(enum netdev_cmd cmd) N(UDP_TUNNEL_DROP_INFO) N(CHANGE_TX_QUEUE_LEN) N(CVLAN_FILTER_PUSH_INFO) N(CVLAN_FILTER_DROP_INFO) N(SVLAN_FILTER_PUSH_INFO) N(SVLAN_FILTER_DROP_INFO) - N(PRE_CHANGEADDR) + N(PRE_CHANGEADDR) N(OFFLOAD_XSTATS_ENABLE) N(OFFLOAD_XSTATS_DISABLE) + N(OFFLOAD_XSTATS_REPORT_USED) N(OFFLOAD_XSTATS_REPORT_DELTA) } #undef N return "UNKNOWN_NETDEV_EVENT"; @@ -2002,6 +1945,32 @@ static int call_netdevice_notifiers_info(unsigned long val, return raw_notifier_call_chain(&netdev_chain, val, info); } +/** + * call_netdevice_notifiers_info_robust - call per-netns notifier blocks + * for and rollback on error + * @val_up: value passed unmodified to notifier function + * @val_down: value passed unmodified to the notifier function when + * recovering from an error on @val_up + * @info: notifier information data + * + * Call all per-netns network notifier blocks, but not notifier blocks on + * the global notifier chain. Parameters and return value are as for + * raw_notifier_call_chain_robust(). + */ + +static int +call_netdevice_notifiers_info_robust(unsigned long val_up, + unsigned long val_down, + struct netdev_notifier_info *info) +{ + struct net *net = dev_net(info->dev); + + ASSERT_RTNL(); + + return raw_notifier_call_chain_robust(&net->netdev_chain, + val_up, val_down, info); +} + static int call_netdevice_notifiers_extack(unsigned long val, struct net_device *dev, struct netlink_ext_ack *extack) @@ -2083,7 +2052,8 @@ void net_dec_egress_queue(void) EXPORT_SYMBOL_GPL(net_dec_egress_queue); #endif -static DEFINE_STATIC_KEY_FALSE(netstamp_needed_key); +DEFINE_STATIC_KEY_FALSE(netstamp_needed_key); +EXPORT_SYMBOL(netstamp_needed_key); #ifdef CONFIG_JUMP_LABEL static atomic_t netstamp_needed_deferred; static atomic_t netstamp_wanted; @@ -2144,14 +2114,15 @@ EXPORT_SYMBOL(net_disable_timestamp); static inline void net_timestamp_set(struct sk_buff *skb) { skb->tstamp = 0; + skb->mono_delivery_time = 0; if (static_branch_unlikely(&netstamp_needed_key)) - __net_timestamp(skb); + skb->tstamp = ktime_get_real(); } #define net_timestamp_check(COND, SKB) \ if (static_branch_unlikely(&netstamp_needed_key)) { \ if ((COND) && !(SKB)->tstamp) \ - __net_timestamp(SKB); \ + (SKB)->tstamp = ktime_get_real(); \ } \ bool is_skb_forwardable(const struct net_device *dev, const struct sk_buff *skb) @@ -3024,15 +2995,73 @@ undo_rx: EXPORT_SYMBOL(netif_set_real_num_queues); /** + * netif_set_tso_max_size() - set the max size of TSO frames supported + * @dev: netdev to update + * @size: max skb->len of a TSO frame + * + * Set the limit on the size of TSO super-frames the device can handle. + * Unless explicitly set the stack will assume the value of + * %GSO_LEGACY_MAX_SIZE. + */ +void netif_set_tso_max_size(struct net_device *dev, unsigned int size) +{ + dev->tso_max_size = min(GSO_MAX_SIZE, size); + if (size < READ_ONCE(dev->gso_max_size)) + netif_set_gso_max_size(dev, size); +} +EXPORT_SYMBOL(netif_set_tso_max_size); + +/** + * netif_set_tso_max_segs() - set the max number of segs supported for TSO + * @dev: netdev to update + * @segs: max number of TCP segments + * + * Set the limit on the number of TCP segments the device can generate from + * a single TSO super-frame. + * Unless explicitly set the stack will assume the value of %GSO_MAX_SEGS. + */ +void netif_set_tso_max_segs(struct net_device *dev, unsigned int segs) +{ + dev->tso_max_segs = segs; + if (segs < READ_ONCE(dev->gso_max_segs)) + netif_set_gso_max_segs(dev, segs); +} +EXPORT_SYMBOL(netif_set_tso_max_segs); + +/** + * netif_inherit_tso_max() - copy all TSO limits from a lower device to an upper + * @to: netdev to update + * @from: netdev from which to copy the limits + */ +void netif_inherit_tso_max(struct net_device *to, const struct net_device *from) +{ + netif_set_tso_max_size(to, from->tso_max_size); + netif_set_tso_max_segs(to, from->tso_max_segs); +} +EXPORT_SYMBOL(netif_inherit_tso_max); + +/** * netif_get_num_default_rss_queues - default number of RSS queues * - * This routine should set an upper limit on the number of RSS queues - * used by default by multiqueue devices. + * Default value is the number of physical cores if there are only 1 or 2, or + * divided by 2 if there are more. */ int netif_get_num_default_rss_queues(void) { - return is_kdump_kernel() ? - 1 : min_t(int, DEFAULT_MAX_NUM_RSS_QUEUES, num_online_cpus()); + cpumask_var_t cpus; + int cpu, count = 0; + + if (unlikely(is_kdump_kernel() || !zalloc_cpumask_var(&cpus, GFP_KERNEL))) + return 1; + + cpumask_copy(cpus, cpu_online_mask); + for_each_cpu(cpu, cpus) { + ++count; + cpumask_andnot(cpus, cpus, topology_sibling_cpumask(cpu)); + } + free_cpumask_var(cpus); + + return count > 2 ? DIV_ROUND_UP(count, 2) : count; } EXPORT_SYMBOL(netif_get_num_default_rss_queues); @@ -3239,12 +3268,18 @@ int skb_checksum_help(struct sk_buff *skb) } offset = skb_checksum_start_offset(skb); - BUG_ON(offset >= skb_headlen(skb)); + ret = -EINVAL; + if (WARN_ON_ONCE(offset >= skb_headlen(skb))) { + DO_ONCE_LITE(skb_dump, KERN_ERR, skb, false); + goto out; + } csum = skb_checksum(skb, offset, skb->len - offset, 0); offset += skb->csum_offset; - BUG_ON(offset + sizeof(__sum16) > skb_headlen(skb)); - + if (WARN_ON_ONCE(offset + sizeof(__sum16) > skb_headlen(skb))) { + DO_ONCE_LITE(skb_dump, KERN_ERR, skb, false); + goto out; + } ret = skb_ensure_writable(skb, offset + sizeof(__sum16)); if (ret) goto out; @@ -3315,40 +3350,6 @@ __be16 skb_network_protocol(struct sk_buff *skb, int *depth) return __vlan_get_protocol(skb, type, depth); } -/** - * skb_mac_gso_segment - mac layer segmentation handler. - * @skb: buffer to segment - * @features: features for the output path (see dev->features) - */ -struct sk_buff *skb_mac_gso_segment(struct sk_buff *skb, - netdev_features_t features) -{ - struct sk_buff *segs = ERR_PTR(-EPROTONOSUPPORT); - struct packet_offload *ptype; - int vlan_depth = skb->mac_len; - __be16 type = skb_network_protocol(skb, &vlan_depth); - - if (unlikely(!type)) - return ERR_PTR(-EINVAL); - - __skb_pull(skb, vlan_depth); - - rcu_read_lock(); - list_for_each_entry_rcu(ptype, &offload_base, list) { - if (ptype->type == type && ptype->callbacks.gso_segment) { - segs = ptype->callbacks.gso_segment(skb, features); - break; - } - } - rcu_read_unlock(); - - __skb_push(skb, skb->data - skb_mac_header(skb)); - - return segs; -} -EXPORT_SYMBOL(skb_mac_gso_segment); - - /* openvswitch calls this on rx path, so we need a different check. */ static inline bool skb_needs_check(struct sk_buff *skb, bool tx_path) @@ -3513,7 +3514,7 @@ static netdev_features_t gso_features_check(const struct sk_buff *skb, { u16 gso_segs = skb_shinfo(skb)->gso_segs; - if (gso_segs > dev->gso_max_segs) + if (gso_segs > READ_ONCE(dev->gso_max_segs)) return features & ~NETIF_F_GSO_MASK; if (!skb_shinfo(skb)->gso_type) { @@ -3585,7 +3586,6 @@ static int xmit_one(struct sk_buff *skb, struct net_device *dev, dev_queue_xmit_nit(skb, dev); len = skb->len; - PRANDOM_ADD_NOISE(skb, dev, txq, len + jiffies); trace_net_dev_start_xmit(skb, dev); rc = netdev_start_xmit(skb, dev, txq, more); trace_net_dev_xmit(skb, rc, dev, len); @@ -3703,7 +3703,7 @@ static struct sk_buff *validate_xmit_skb(struct sk_buff *skb, struct net_device out_kfree_skb: kfree_skb(skb); out_null: - atomic_long_inc(&dev->tx_dropped); + dev_core_stats_tx_dropped_inc(dev); return NULL; } @@ -3827,7 +3827,8 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, no_lock_out: if (unlikely(to_free)) - kfree_skb_list(to_free); + kfree_skb_list_reason(to_free, + SKB_DROP_REASON_QDISC_DROP); return rc; } @@ -3836,8 +3837,12 @@ no_lock_out: * separate lock before trying to get qdisc main lock. * This permits qdisc->running owner to get the lock more * often and dequeue packets faster. + * On PREEMPT_RT it is possible to preempt the qdisc owner during xmit + * and then other tasks will only enqueue packets. The packets will be + * sent after the qdisc owner is scheduled again. To prevent this + * scenario the task always serialize on the lock. */ - contended = qdisc_is_running(q); + contended = qdisc_is_running(q) || IS_ENABLED(CONFIG_PREEMPT_RT); if (unlikely(contended)) spin_lock(&q->busylock); @@ -3878,7 +3883,7 @@ no_lock_out: } spin_unlock(root_lock); if (unlikely(to_free)) - kfree_skb_list(to_free); + kfree_skb_list_reason(to_free, SKB_DROP_REASON_QDISC_DROP); if (unlikely(contended)) spin_unlock(&q->busylock); return rc; @@ -3922,9 +3927,9 @@ int dev_loopback_xmit(struct net *net, struct sock *sk, struct sk_buff *skb) skb->pkt_type = PACKET_LOOPBACK; if (skb->ip_summed == CHECKSUM_NONE) skb->ip_summed = CHECKSUM_UNNECESSARY; - WARN_ON(!skb_dst(skb)); + DEBUG_NET_WARN_ON_ONCE(!skb_dst(skb)); skb_dst_force(skb); - netif_rx_ni(skb); + netif_rx(skb); return 0; } EXPORT_SYMBOL(dev_loopback_xmit); @@ -3941,8 +3946,8 @@ sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev) return skb; /* qdisc_skb_cb(skb)->pkt_len was already set by the caller. */ - qdisc_skb_cb(skb)->mru = 0; - qdisc_skb_cb(skb)->post_ct = false; + tc_skb_cb(skb)->mru = 0; + tc_skb_cb(skb)->post_ct = false; mini_qdisc_bstats_cpu_update(miniq, skb); switch (tcf_classify(skb, miniq->block, miniq->filter_list, &cl_res, false)) { @@ -3953,7 +3958,7 @@ sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev) case TC_ACT_SHOT: mini_qdisc_qstats_cpu_drop(miniq); *ret = NET_XMIT_DROP; - kfree_skb(skb); + kfree_skb_reason(skb, SKB_DROP_REASON_TC_EGRESS); return NULL; case TC_ACT_STOLEN: case TC_ACT_QUEUED: @@ -3973,6 +3978,25 @@ sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev) return skb; } + +static struct netdev_queue * +netdev_tx_queue_mapping(struct net_device *dev, struct sk_buff *skb) +{ + int qm = skb_get_queue_mapping(skb); + + return netdev_get_tx_queue(dev, netdev_cap_txqueue(dev, qm)); +} + +static bool netdev_xmit_txqueue_skipped(void) +{ + return __this_cpu_read(softnet_data.xmit.skip_txqueue); +} + +void netdev_xmit_skip_txqueue(bool skip) +{ + __this_cpu_write(softnet_data.xmit.skip_txqueue, skip); +} +EXPORT_SYMBOL_GPL(netdev_xmit_skip_txqueue); #endif /* CONFIG_NET_EGRESS */ #ifdef CONFIG_XPS @@ -4115,40 +4139,36 @@ struct netdev_queue *netdev_core_pick_tx(struct net_device *dev, } /** - * __dev_queue_xmit - transmit a buffer - * @skb: buffer to transmit - * @sb_dev: suboordinate device used for L2 forwarding offload - * - * Queue a buffer for transmission to a network device. The caller must - * have set the device and priority and built the buffer before calling - * this function. The function can be called from an interrupt. + * __dev_queue_xmit() - transmit a buffer + * @skb: buffer to transmit + * @sb_dev: suboordinate device used for L2 forwarding offload * - * A negative errno code is returned on a failure. A success does not - * guarantee the frame will be transmitted as it may be dropped due - * to congestion or traffic shaping. + * Queue a buffer for transmission to a network device. The caller must + * have set the device and priority and built the buffer before calling + * this function. The function can be called from an interrupt. * - * ----------------------------------------------------------------------------------- - * I notice this method can also return errors from the queue disciplines, - * including NET_XMIT_DROP, which is a positive value. So, errors can also - * be positive. + * When calling this method, interrupts MUST be enabled. This is because + * the BH enable code must have IRQs enabled so that it will not deadlock. * - * Regardless of the return value, the skb is consumed, so it is currently - * difficult to retry a send to this method. (You can bump the ref count - * before sending to hold a reference for retry if you are careful.) + * Regardless of the return value, the skb is consumed, so it is currently + * difficult to retry a send to this method. (You can bump the ref count + * before sending to hold a reference for retry if you are careful.) * - * When calling this method, interrupts MUST be enabled. This is because - * the BH enable code must have IRQs enabled so that it will not deadlock. - * --BLG + * Return: + * * 0 - buffer successfully transmitted + * * positive qdisc return code - NET_XMIT_DROP etc. + * * negative errno - other errors */ -static int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev) +int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev) { struct net_device *dev = skb->dev; - struct netdev_queue *txq; + struct netdev_queue *txq = NULL; struct Qdisc *q; int rc = -ENOMEM; bool again = false; skb_reset_mac_header(skb); + skb_assert_len(skb); if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_SCHED_TSTAMP)) __skb_tstamp_tx(skb, NULL, NULL, skb->sk, SCM_TSTAMP_SCHED); @@ -4171,11 +4191,17 @@ static int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev) if (!skb) goto out; } + + netdev_xmit_skip_txqueue(false); + nf_skip_egress(skb, true); skb = sch_handle_egress(skb, &rc, dev); if (!skb) goto out; nf_skip_egress(skb, false); + + if (netdev_xmit_txqueue_skipped()) + txq = netdev_tx_queue_mapping(dev, skb); } #endif /* If device/qdisc don't need skb->dst, release it right now while @@ -4186,7 +4212,9 @@ static int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev) else skb_dst_force(skb); - txq = netdev_core_pick_tx(dev, skb, sb_dev); + if (!txq) + txq = netdev_core_pick_tx(dev, skb, sb_dev); + q = rcu_dereference_bh(txq->qdisc); trace_net_dev_queue(skb); @@ -4221,7 +4249,6 @@ static int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev) if (!skb) goto out; - PRANDOM_ADD_NOISE(skb, dev, txq, jiffies); HARD_TX_LOCK(dev, txq, cpu); if (!netif_xmit_stopped(txq)) { @@ -4249,25 +4276,14 @@ recursion_alert: rc = -ENETDOWN; rcu_read_unlock_bh(); - atomic_long_inc(&dev->tx_dropped); + dev_core_stats_tx_dropped_inc(dev); kfree_skb_list(skb); return rc; out: rcu_read_unlock_bh(); return rc; } - -int dev_queue_xmit(struct sk_buff *skb) -{ - return __dev_queue_xmit(skb, NULL); -} -EXPORT_SYMBOL(dev_queue_xmit); - -int dev_queue_xmit_accel(struct sk_buff *skb, struct net_device *sb_dev) -{ - return __dev_queue_xmit(skb, sb_dev); -} -EXPORT_SYMBOL(dev_queue_xmit_accel); +EXPORT_SYMBOL(__dev_queue_xmit); int __dev_direct_xmit(struct sk_buff *skb, u16 queue_id) { @@ -4287,7 +4303,6 @@ int __dev_direct_xmit(struct sk_buff *skb, u16 queue_id) skb_set_queue_mapping(skb, queue_id); txq = skb_get_tx_queue(dev, skb); - PRANDOM_ADD_NOISE(skb, dev, txq, jiffies); local_bh_disable(); @@ -4301,7 +4316,7 @@ int __dev_direct_xmit(struct sk_buff *skb, u16 queue_id) local_bh_enable(); return ret; drop: - atomic_long_inc(&dev->tx_dropped); + dev_core_stats_tx_dropped_inc(dev); kfree_skb_list(skb); return NET_XMIT_DROP; } @@ -4315,6 +4330,7 @@ int netdev_max_backlog __read_mostly = 1000; EXPORT_SYMBOL(netdev_max_backlog); int netdev_tstamp_prequeue __read_mostly = 1; +unsigned int sysctl_skb_defer_max __read_mostly = 64; int netdev_budget __read_mostly = 300; /* Must be at least 2 jiffes to guarantee 1 jiffy timeout */ unsigned int __read_mostly netdev_budget_usecs = 2 * USEC_PER_SEC / HZ; @@ -4323,8 +4339,6 @@ int dev_weight_rx_bias __read_mostly = 1; /* bias for backlog weight */ int dev_weight_tx_bias __read_mostly = 1; /* bias for output_queue quota */ int dev_rx_weight __read_mostly = 64; int dev_tx_weight __read_mostly = 64; -/* Maximum number of GRO_NORMAL skbs to batch up for list-RX */ -int gro_normal_batch __read_mostly = 8; /* Called with irq disabled */ static inline void ____napi_schedule(struct softnet_data *sd, @@ -4332,6 +4346,8 @@ static inline void ____napi_schedule(struct softnet_data *sd, { struct task_struct *thread; + lockdep_assert_irqs_disabled(); + if (test_bit(NAPI_STATE_THREADED, &napi->state)) { /* Paired with smp_mb__before_atomic() in * napi_enable()/dev_set_threaded(). @@ -4566,16 +4582,25 @@ static void rps_trigger_softirq(void *data) #endif /* CONFIG_RPS */ +/* Called from hardirq (IPI) context */ +static void trigger_rx_softirq(void *data) +{ + struct softnet_data *sd = data; + + __raise_softirq_irqoff(NET_RX_SOFTIRQ); + smp_store_release(&sd->defer_ipi_scheduled, 0); +} + /* * Check if this softnet_data structure is another cpu one * If yes, queue it to our IPI list and return 1 * If no, return 0 */ -static int rps_ipi_queued(struct softnet_data *sd) +static int napi_schedule_rps(struct softnet_data *sd) { -#ifdef CONFIG_RPS struct softnet_data *mysd = this_cpu_ptr(&softnet_data); +#ifdef CONFIG_RPS if (sd != mysd) { sd->rps_ipi_next = mysd->rps_ipi_list; mysd->rps_ipi_list = sd; @@ -4584,6 +4609,7 @@ static int rps_ipi_queued(struct softnet_data *sd) return 1; } #endif /* CONFIG_RPS */ + __napi_schedule_irqoff(&mysd->backlog); return 0; } @@ -4598,7 +4624,7 @@ static bool skb_flow_limit(struct sk_buff *skb, unsigned int qlen) struct softnet_data *sd; unsigned int old_flow, new_flow; - if (qlen < (netdev_max_backlog >> 1)) + if (qlen < (READ_ONCE(netdev_max_backlog) >> 1)) return false; sd = this_cpu_ptr(&softnet_data); @@ -4634,46 +4660,42 @@ static bool skb_flow_limit(struct sk_buff *skb, unsigned int qlen) static int enqueue_to_backlog(struct sk_buff *skb, int cpu, unsigned int *qtail) { + enum skb_drop_reason reason; struct softnet_data *sd; unsigned long flags; unsigned int qlen; + reason = SKB_DROP_REASON_NOT_SPECIFIED; sd = &per_cpu(softnet_data, cpu); - local_irq_save(flags); - - rps_lock(sd); + rps_lock_irqsave(sd, &flags); if (!netif_running(skb->dev)) goto drop; qlen = skb_queue_len(&sd->input_pkt_queue); - if (qlen <= netdev_max_backlog && !skb_flow_limit(skb, qlen)) { + if (qlen <= READ_ONCE(netdev_max_backlog) && !skb_flow_limit(skb, qlen)) { if (qlen) { enqueue: __skb_queue_tail(&sd->input_pkt_queue, skb); input_queue_tail_incr_save(sd, qtail); - rps_unlock(sd); - local_irq_restore(flags); + rps_unlock_irq_restore(sd, &flags); return NET_RX_SUCCESS; } /* Schedule NAPI for backlog device * We can use non atomic operation since we own the queue lock */ - if (!__test_and_set_bit(NAPI_STATE_SCHED, &sd->backlog.state)) { - if (!rps_ipi_queued(sd)) - ____napi_schedule(sd, &sd->backlog); - } + if (!__test_and_set_bit(NAPI_STATE_SCHED, &sd->backlog.state)) + napi_schedule_rps(sd); goto enqueue; } + reason = SKB_DROP_REASON_CPU_BACKLOG; drop: sd->dropped++; - rps_unlock(sd); + rps_unlock_irq_restore(sd, &flags); - local_irq_restore(flags); - - atomic_long_inc(&skb->dev->rx_dropped); - kfree_skb(skb); + dev_core_stats_rx_dropped_inc(skb->dev); + kfree_skb_reason(skb, reason); return NET_RX_DROP; } @@ -4827,7 +4849,7 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb, case XDP_PASS: break; default: - bpf_warn_invalid_xdp_action(act); + bpf_warn_invalid_xdp_action(skb->dev, xdp_prog, act); fallthrough; case XDP_ABORTED: trace_xdp_exception(skb->dev, xdp_prog, act); @@ -4842,7 +4864,10 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb, } /* When doing generic XDP we have to bypass the qdisc layer and the - * network taps in order to match in-driver-XDP behavior. + * network taps in order to match in-driver-XDP behavior. This also means + * that XDP packets are able to starve other packets going through a qdisc, + * and DDOS attacks will be more effective. In-driver-XDP use dedicated TX + * queues, so they do not have this starvation issue. */ void generic_xdp_tx(struct sk_buff *skb, struct bpf_prog *xdp_prog) { @@ -4854,7 +4879,7 @@ void generic_xdp_tx(struct sk_buff *skb, struct bpf_prog *xdp_prog) txq = netdev_core_pick_tx(dev, skb, NULL); cpu = smp_processor_id(); HARD_TX_LOCK(dev, txq, cpu); - if (!netif_xmit_stopped(txq)) { + if (!netif_xmit_frozen_or_drv_stopped(txq)) { rc = netdev_start_xmit(skb, dev, txq, 0); if (dev_xmit_complete(rc)) free_skb = false; @@ -4862,6 +4887,7 @@ void generic_xdp_tx(struct sk_buff *skb, struct bpf_prog *xdp_prog) HARD_TX_UNLOCK(dev, txq); if (free_skb) { trace_xdp_exception(dev, xdp_prog, XDP_TX); + dev_core_stats_tx_dropped_inc(dev); kfree_skb(skb); } } @@ -4893,7 +4919,7 @@ int do_xdp_generic(struct bpf_prog *xdp_prog, struct sk_buff *skb) } return XDP_PASS; out_redir: - kfree_skb(skb); + kfree_skb_reason(skb, SKB_DROP_REASON_XDP); return XDP_DROP; } EXPORT_SYMBOL_GPL(do_xdp_generic); @@ -4902,7 +4928,7 @@ static int netif_rx_internal(struct sk_buff *skb) { int ret; - net_timestamp_check(netdev_tstamp_prequeue, skb); + net_timestamp_check(READ_ONCE(netdev_tstamp_prequeue), skb); trace_netif_rx(skb); @@ -4911,7 +4937,6 @@ static int netif_rx_internal(struct sk_buff *skb) struct rps_dev_flow voidflow, *rflow = &voidflow; int cpu; - preempt_disable(); rcu_read_lock(); cpu = get_rps_cpu(skb->dev, skb, &rflow); @@ -4921,78 +4946,72 @@ static int netif_rx_internal(struct sk_buff *skb) ret = enqueue_to_backlog(skb, cpu, &rflow->last_qtail); rcu_read_unlock(); - preempt_enable(); } else #endif { unsigned int qtail; - ret = enqueue_to_backlog(skb, get_cpu(), &qtail); - put_cpu(); + ret = enqueue_to_backlog(skb, smp_processor_id(), &qtail); } return ret; } /** + * __netif_rx - Slightly optimized version of netif_rx + * @skb: buffer to post + * + * This behaves as netif_rx except that it does not disable bottom halves. + * As a result this function may only be invoked from the interrupt context + * (either hard or soft interrupt). + */ +int __netif_rx(struct sk_buff *skb) +{ + int ret; + + lockdep_assert_once(hardirq_count() | softirq_count()); + + trace_netif_rx_entry(skb); + ret = netif_rx_internal(skb); + trace_netif_rx_exit(ret); + return ret; +} +EXPORT_SYMBOL(__netif_rx); + +/** * netif_rx - post buffer to the network code * @skb: buffer to post * * This function receives a packet from a device driver and queues it for - * the upper (protocol) levels to process. It always succeeds. The buffer - * may be dropped during processing for congestion control or by the - * protocol layers. + * the upper (protocol) levels to process via the backlog NAPI device. It + * always succeeds. The buffer may be dropped during processing for + * congestion control or by the protocol layers. + * The network buffer is passed via the backlog NAPI device. Modern NIC + * driver should use NAPI and GRO. + * This function can used from interrupt and from process context. The + * caller from process context must not disable interrupts before invoking + * this function. * * return values: * NET_RX_SUCCESS (no congestion) * NET_RX_DROP (packet was dropped) * */ - int netif_rx(struct sk_buff *skb) { + bool need_bh_off = !(hardirq_count() | softirq_count()); int ret; + if (need_bh_off) + local_bh_disable(); trace_netif_rx_entry(skb); - ret = netif_rx_internal(skb); trace_netif_rx_exit(ret); - + if (need_bh_off) + local_bh_enable(); return ret; } EXPORT_SYMBOL(netif_rx); -int netif_rx_ni(struct sk_buff *skb) -{ - int err; - - trace_netif_rx_ni_entry(skb); - - preempt_disable(); - err = netif_rx_internal(skb); - if (local_softirq_pending()) - do_softirq(); - preempt_enable(); - trace_netif_rx_ni_exit(err); - - return err; -} -EXPORT_SYMBOL(netif_rx_ni); - -int netif_rx_any_context(struct sk_buff *skb) -{ - /* - * If invoked from contexts which do not invoke bottom half - * processing either at return from interrupt or when softrqs are - * reenabled, use netif_rx_ni() which invokes bottomhalf processing - * directly. - */ - if (in_interrupt()) - return netif_rx(skb); - else - return netif_rx_ni(skb); -} -EXPORT_SYMBOL(netif_rx_any_context); - static __latent_entropy void net_tx_action(struct softirq_action *h) { struct softnet_data *sd = this_cpu_ptr(&softnet_data); @@ -5014,7 +5033,8 @@ static __latent_entropy void net_tx_action(struct softirq_action *h) if (likely(get_kfree_skb_cb(skb)->reason == SKB_REASON_CONSUMED)) trace_consume_skb(skb); else - trace_kfree_skb(skb, net_tx_action); + trace_kfree_skb(skb, net_tx_action, + SKB_DROP_REASON_NOT_SPECIFIED); if (skb->fclone != SKB_FCLONE_UNAVAILABLE) __kfree_skb(skb); @@ -5103,8 +5123,8 @@ sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret, } qdisc_skb_cb(skb)->pkt_len = skb->len; - qdisc_skb_cb(skb)->mru = 0; - qdisc_skb_cb(skb)->post_ct = false; + tc_skb_cb(skb)->mru = 0; + tc_skb_cb(skb)->post_ct = false; skb->tc_at_ingress = 1; mini_qdisc_bstats_cpu_update(miniq, skb); @@ -5115,12 +5135,14 @@ sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret, break; case TC_ACT_SHOT: mini_qdisc_qstats_cpu_drop(miniq); - kfree_skb(skb); + kfree_skb_reason(skb, SKB_DROP_REASON_TC_INGRESS); + *ret = NET_RX_DROP; return NULL; case TC_ACT_STOLEN: case TC_ACT_QUEUED: case TC_ACT_TRAP: consume_skb(skb); + *ret = NET_RX_SUCCESS; return NULL; case TC_ACT_REDIRECT: /* skb_mac_header check was done by cls/act_bpf, so @@ -5133,8 +5155,10 @@ sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret, *another = true; break; } + *ret = NET_RX_SUCCESS; return NULL; case TC_ACT_CONSUMED: + *ret = NET_RX_SUCCESS; return NULL; default: break; @@ -5261,7 +5285,7 @@ static int __netif_receive_skb_core(struct sk_buff **pskb, bool pfmemalloc, int ret = NET_RX_DROP; __be16 type; - net_timestamp_check(!netdev_tstamp_prequeue, skb); + net_timestamp_check(!READ_ONCE(netdev_tstamp_prequeue), skb); trace_netif_receive_skb(skb); @@ -5433,10 +5457,10 @@ check_vlan_id: } else { drop: if (!deliver_exact) - atomic_long_inc(&skb->dev->rx_dropped); + dev_core_stats_rx_dropped_inc(skb->dev); else - atomic_long_inc(&skb->dev->rx_nohandler); - kfree_skb(skb); + dev_core_stats_rx_nohandler_inc(skb->dev); + kfree_skb_reason(skb, SKB_DROP_REASON_UNHANDLED_PROTO); /* Jamal, now you will not able to escape explaining * me how you were going to use this. :-) */ @@ -5644,7 +5668,7 @@ static int netif_receive_skb_internal(struct sk_buff *skb) { int ret; - net_timestamp_check(netdev_tstamp_prequeue, skb); + net_timestamp_check(READ_ONCE(netdev_tstamp_prequeue), skb); if (skb_defer_rx_timestamp(skb)) return NET_RX_SUCCESS; @@ -5667,14 +5691,14 @@ static int netif_receive_skb_internal(struct sk_buff *skb) return ret; } -static void netif_receive_skb_list_internal(struct list_head *head) +void netif_receive_skb_list_internal(struct list_head *head) { struct sk_buff *skb, *next; struct list_head sublist; INIT_LIST_HEAD(&sublist); list_for_each_entry_safe(skb, next, head, list) { - net_timestamp_check(netdev_tstamp_prequeue, skb); + net_timestamp_check(READ_ONCE(netdev_tstamp_prequeue), skb); skb_list_del_init(skb); if (!skb_defer_rx_timestamp(skb)) list_add_tail(&skb->list, &sublist); @@ -5764,8 +5788,7 @@ static void flush_backlog(struct work_struct *work) local_bh_disable(); sd = this_cpu_ptr(&softnet_data); - local_irq_disable(); - rps_lock(sd); + rps_lock_irq_disable(sd); skb_queue_walk_safe(&sd->input_pkt_queue, skb, tmp) { if (skb->dev->reg_state == NETREG_UNREGISTERING) { __skb_unlink(skb, &sd->input_pkt_queue); @@ -5773,8 +5796,7 @@ static void flush_backlog(struct work_struct *work) input_queue_head_incr(sd); } } - rps_unlock(sd); - local_irq_enable(); + rps_unlock_irq_enable(sd); skb_queue_walk_safe(&sd->process_queue, skb, tmp) { if (skb->dev->reg_state == NETREG_UNREGISTERING) { @@ -5792,16 +5814,14 @@ static bool flush_required(int cpu) struct softnet_data *sd = &per_cpu(softnet_data, cpu); bool do_flush; - local_irq_disable(); - rps_lock(sd); + rps_lock_irq_disable(sd); /* as insertion into process_queue happens with the rps lock held, * process_queue access may race only with dequeue */ do_flush = !skb_queue_empty(&sd->input_pkt_queue) || !skb_queue_empty_lockless(&sd->process_queue); - rps_unlock(sd); - local_irq_enable(); + rps_unlock_irq_enable(sd); return do_flush; #endif @@ -5845,550 +5865,6 @@ static void flush_all_backlogs(void) cpus_read_unlock(); } -/* Pass the currently batched GRO_NORMAL SKBs up to the stack. */ -static void gro_normal_list(struct napi_struct *napi) -{ - if (!napi->rx_count) - return; - netif_receive_skb_list_internal(&napi->rx_list); - INIT_LIST_HEAD(&napi->rx_list); - napi->rx_count = 0; -} - -/* Queue one GRO_NORMAL SKB up for list processing. If batch size exceeded, - * pass the whole batch up to the stack. - */ -static void gro_normal_one(struct napi_struct *napi, struct sk_buff *skb, int segs) -{ - list_add_tail(&skb->list, &napi->rx_list); - napi->rx_count += segs; - if (napi->rx_count >= gro_normal_batch) - gro_normal_list(napi); -} - -static void napi_gro_complete(struct napi_struct *napi, struct sk_buff *skb) -{ - struct packet_offload *ptype; - __be16 type = skb->protocol; - struct list_head *head = &offload_base; - int err = -ENOENT; - - BUILD_BUG_ON(sizeof(struct napi_gro_cb) > sizeof(skb->cb)); - - if (NAPI_GRO_CB(skb)->count == 1) { - skb_shinfo(skb)->gso_size = 0; - goto out; - } - - rcu_read_lock(); - list_for_each_entry_rcu(ptype, head, list) { - if (ptype->type != type || !ptype->callbacks.gro_complete) - continue; - - err = INDIRECT_CALL_INET(ptype->callbacks.gro_complete, - ipv6_gro_complete, inet_gro_complete, - skb, 0); - break; - } - rcu_read_unlock(); - - if (err) { - WARN_ON(&ptype->list == head); - kfree_skb(skb); - return; - } - -out: - gro_normal_one(napi, skb, NAPI_GRO_CB(skb)->count); -} - -static void __napi_gro_flush_chain(struct napi_struct *napi, u32 index, - bool flush_old) -{ - struct list_head *head = &napi->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--; - } - - if (!napi->gro_hash[index].count) - __clear_bit(index, &napi->gro_bitmask); -} - -/* napi->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) -{ - unsigned long bitmask = napi->gro_bitmask; - unsigned int i, base = ~0U; - - while ((i = ffs(bitmask)) != 0) { - bitmask >>= i; - base += i; - __napi_gro_flush_chain(napi, base, flush_old); - } -} -EXPORT_SYMBOL(napi_gro_flush); - -static void gro_list_prepare(const struct list_head *head, - const struct sk_buff *skb) -{ - unsigned int maclen = skb->dev->hard_header_len; - u32 hash = skb_get_hash_raw(skb); - struct sk_buff *p; - - list_for_each_entry(p, head, list) { - unsigned long diffs; - - NAPI_GRO_CB(p)->flush = 0; - - if (hash != skb_get_hash_raw(p)) { - NAPI_GRO_CB(p)->same_flow = 0; - continue; - } - - diffs = (unsigned long)p->dev ^ (unsigned long)skb->dev; - diffs |= skb_vlan_tag_present(p) ^ skb_vlan_tag_present(skb); - if (skb_vlan_tag_present(p)) - diffs |= skb_vlan_tag_get(p) ^ skb_vlan_tag_get(skb); - diffs |= skb_metadata_differs(p, skb); - if (maclen == ETH_HLEN) - diffs |= compare_ether_header(skb_mac_header(p), - skb_mac_header(skb)); - else if (!diffs) - diffs = memcmp(skb_mac_header(p), - skb_mac_header(skb), - maclen); - - /* in most common scenarions 'slow_gro' is 0 - * otherwise we are already on some slower paths - * either skip all the infrequent tests altogether or - * avoid trying too hard to skip each of them individually - */ - if (!diffs && unlikely(skb->slow_gro | p->slow_gro)) { -#if IS_ENABLED(CONFIG_SKB_EXTENSIONS) && IS_ENABLED(CONFIG_NET_TC_SKB_EXT) - struct tc_skb_ext *skb_ext; - struct tc_skb_ext *p_ext; -#endif - - diffs |= p->sk != skb->sk; - diffs |= skb_metadata_dst_cmp(p, skb); - diffs |= skb_get_nfct(p) ^ skb_get_nfct(skb); - -#if IS_ENABLED(CONFIG_SKB_EXTENSIONS) && IS_ENABLED(CONFIG_NET_TC_SKB_EXT) - skb_ext = skb_ext_find(skb, TC_SKB_EXT); - p_ext = skb_ext_find(p, TC_SKB_EXT); - - diffs |= (!!p_ext) ^ (!!skb_ext); - if (!diffs && unlikely(skb_ext)) - diffs |= p_ext->chain ^ skb_ext->chain; -#endif - } - - NAPI_GRO_CB(p)->same_flow = !diffs; - } -} - -static inline void skb_gro_reset_offset(struct sk_buff *skb, u32 nhoff) -{ - const struct skb_shared_info *pinfo = skb_shinfo(skb); - const skb_frag_t *frag0 = &pinfo->frags[0]; - - NAPI_GRO_CB(skb)->data_offset = 0; - NAPI_GRO_CB(skb)->frag0 = NULL; - NAPI_GRO_CB(skb)->frag0_len = 0; - - if (!skb_headlen(skb) && pinfo->nr_frags && - !PageHighMem(skb_frag_page(frag0)) && - (!NET_IP_ALIGN || !((skb_frag_off(frag0) + nhoff) & 3))) { - NAPI_GRO_CB(skb)->frag0 = skb_frag_address(frag0); - NAPI_GRO_CB(skb)->frag0_len = min_t(unsigned int, - skb_frag_size(frag0), - skb->end - skb->tail); - } -} - -static void gro_pull_from_frag0(struct sk_buff *skb, int grow) -{ - struct skb_shared_info *pinfo = skb_shinfo(skb); - - BUG_ON(skb->end - skb->tail < grow); - - memcpy(skb_tail_pointer(skb), NAPI_GRO_CB(skb)->frag0, grow); - - skb->data_len -= grow; - skb->tail += grow; - - skb_frag_off_add(&pinfo->frags[0], grow); - skb_frag_size_sub(&pinfo->frags[0], grow); - - if (unlikely(!skb_frag_size(&pinfo->frags[0]))) { - skb_frag_unref(skb, 0); - memmove(pinfo->frags, pinfo->frags + 1, - --pinfo->nr_frags * sizeof(pinfo->frags[0])); - } -} - -static void gro_flush_oldest(struct napi_struct *napi, struct list_head *head) -{ - struct sk_buff *oldest; - - oldest = list_last_entry(head, struct sk_buff, list); - - /* We are called with head length >= MAX_GRO_SKBS, so this is - * impossible. - */ - if (WARN_ON_ONCE(!oldest)) - return; - - /* Do not adjust napi->gro_hash[].count, caller is adding a new - * SKB to the chain. - */ - skb_list_del_init(oldest); - napi_gro_complete(napi, oldest); -} - -static enum gro_result dev_gro_receive(struct napi_struct *napi, 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 = &offload_base; - struct packet_offload *ptype; - __be16 type = skb->protocol; - struct sk_buff *pp = NULL; - enum gro_result ret; - int same_flow; - int grow; - - if (netif_elide_gro(skb->dev)) - goto normal; - - gro_list_prepare(&gro_list->list, skb); - - rcu_read_lock(); - list_for_each_entry_rcu(ptype, head, list) { - if (ptype->type != type || !ptype->callbacks.gro_receive) - continue; - - skb_set_network_header(skb, skb_gro_offset(skb)); - skb_reset_mac_len(skb); - NAPI_GRO_CB(skb)->same_flow = 0; - NAPI_GRO_CB(skb)->flush = skb_is_gso(skb) || skb_has_frag_list(skb); - NAPI_GRO_CB(skb)->free = 0; - NAPI_GRO_CB(skb)->encap_mark = 0; - NAPI_GRO_CB(skb)->recursion_counter = 0; - NAPI_GRO_CB(skb)->is_fou = 0; - NAPI_GRO_CB(skb)->is_atomic = 1; - NAPI_GRO_CB(skb)->gro_remcsum_start = 0; - - /* Setup for GRO checksum validation */ - switch (skb->ip_summed) { - case CHECKSUM_COMPLETE: - NAPI_GRO_CB(skb)->csum = skb->csum; - NAPI_GRO_CB(skb)->csum_valid = 1; - NAPI_GRO_CB(skb)->csum_cnt = 0; - break; - case CHECKSUM_UNNECESSARY: - NAPI_GRO_CB(skb)->csum_cnt = skb->csum_level + 1; - NAPI_GRO_CB(skb)->csum_valid = 0; - break; - default: - NAPI_GRO_CB(skb)->csum_cnt = 0; - NAPI_GRO_CB(skb)->csum_valid = 0; - } - - pp = INDIRECT_CALL_INET(ptype->callbacks.gro_receive, - ipv6_gro_receive, inet_gro_receive, - &gro_list->list, skb); - break; - } - rcu_read_unlock(); - - if (&ptype->list == head) - goto normal; - - if (PTR_ERR(pp) == -EINPROGRESS) { - ret = GRO_CONSUMED; - goto ok; - } - - same_flow = NAPI_GRO_CB(skb)->same_flow; - ret = NAPI_GRO_CB(skb)->free ? GRO_MERGED_FREE : GRO_MERGED; - - if (pp) { - skb_list_del_init(pp); - napi_gro_complete(napi, pp); - gro_list->count--; - } - - if (same_flow) - goto ok; - - if (NAPI_GRO_CB(skb)->flush) - goto normal; - - if (unlikely(gro_list->count >= MAX_GRO_SKBS)) - gro_flush_oldest(napi, &gro_list->list); - else - gro_list->count++; - - NAPI_GRO_CB(skb)->count = 1; - NAPI_GRO_CB(skb)->age = jiffies; - NAPI_GRO_CB(skb)->last = skb; - skb_shinfo(skb)->gso_size = skb_gro_len(skb); - list_add(&skb->list, &gro_list->list); - ret = GRO_HELD; - -pull: - grow = skb_gro_offset(skb) - skb_headlen(skb); - if (grow > 0) - gro_pull_from_frag0(skb, grow); -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); - } - - return ret; - -normal: - ret = GRO_NORMAL; - goto pull; -} - -struct packet_offload *gro_find_receive_by_type(__be16 type) -{ - struct list_head *offload_head = &offload_base; - struct packet_offload *ptype; - - list_for_each_entry_rcu(ptype, offload_head, list) { - if (ptype->type != type || !ptype->callbacks.gro_receive) - continue; - return ptype; - } - return NULL; -} -EXPORT_SYMBOL(gro_find_receive_by_type); - -struct packet_offload *gro_find_complete_by_type(__be16 type) -{ - struct list_head *offload_head = &offload_base; - struct packet_offload *ptype; - - list_for_each_entry_rcu(ptype, offload_head, list) { - if (ptype->type != type || !ptype->callbacks.gro_complete) - continue; - return ptype; - } - return NULL; -} -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) -{ - switch (ret) { - case GRO_NORMAL: - gro_normal_one(napi, skb, 1); - break; - - case GRO_MERGED_FREE: - if (NAPI_GRO_CB(skb)->free == NAPI_GRO_FREE_STOLEN_HEAD) - napi_skb_free_stolen_head(skb); - else if (skb->fclone != SKB_FCLONE_UNAVAILABLE) - __kfree_skb(skb); - else - __kfree_skb_defer(skb); - break; - - case GRO_HELD: - case GRO_MERGED: - case GRO_CONSUMED: - break; - } - - return ret; -} - -gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb) -{ - gro_result_t ret; - - skb_mark_napi_id(skb, napi); - trace_napi_gro_receive_entry(skb); - - skb_gro_reset_offset(skb, 0); - - ret = napi_skb_finish(napi, skb, dev_gro_receive(napi, skb)); - trace_napi_gro_receive_exit(ret); - - return ret; -} -EXPORT_SYMBOL(napi_gro_receive); - -static void napi_reuse_skb(struct napi_struct *napi, struct sk_buff *skb) -{ - if (unlikely(skb->pfmemalloc)) { - consume_skb(skb); - return; - } - __skb_pull(skb, skb_headlen(skb)); - /* restore the reserve we had after netdev_alloc_skb_ip_align() */ - skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN - skb_headroom(skb)); - __vlan_hwaccel_clear_tag(skb); - skb->dev = napi->dev; - skb->skb_iif = 0; - - /* eth_type_trans() assumes pkt_type is PACKET_HOST */ - skb->pkt_type = PACKET_HOST; - - skb->encapsulation = 0; - skb_shinfo(skb)->gso_type = 0; - skb->truesize = SKB_TRUESIZE(skb_end_offset(skb)); - if (unlikely(skb->slow_gro)) { - skb_orphan(skb); - skb_ext_reset(skb); - nf_reset_ct(skb); - skb->slow_gro = 0; - } - - napi->skb = skb; -} - -struct sk_buff *napi_get_frags(struct napi_struct *napi) -{ - struct sk_buff *skb = napi->skb; - - if (!skb) { - skb = napi_alloc_skb(napi, GRO_MAX_HEAD); - if (skb) { - napi->skb = skb; - skb_mark_napi_id(skb, napi); - } - } - return skb; -} -EXPORT_SYMBOL(napi_get_frags); - -static gro_result_t napi_frags_finish(struct napi_struct *napi, - struct sk_buff *skb, - gro_result_t ret) -{ - switch (ret) { - case GRO_NORMAL: - case GRO_HELD: - __skb_push(skb, ETH_HLEN); - skb->protocol = eth_type_trans(skb, skb->dev); - if (ret == GRO_NORMAL) - gro_normal_one(napi, skb, 1); - break; - - case GRO_MERGED_FREE: - if (NAPI_GRO_CB(skb)->free == NAPI_GRO_FREE_STOLEN_HEAD) - napi_skb_free_stolen_head(skb); - else - napi_reuse_skb(napi, skb); - break; - - case GRO_MERGED: - case GRO_CONSUMED: - break; - } - - return ret; -} - -/* Upper GRO stack assumes network header starts at gro_offset=0 - * Drivers could call both napi_gro_frags() and napi_gro_receive() - * We copy ethernet header into skb->data to have a common layout. - */ -static struct sk_buff *napi_frags_skb(struct napi_struct *napi) -{ - struct sk_buff *skb = napi->skb; - const struct ethhdr *eth; - unsigned int hlen = sizeof(*eth); - - napi->skb = NULL; - - skb_reset_mac_header(skb); - skb_gro_reset_offset(skb, hlen); - - if (unlikely(skb_gro_header_hard(skb, hlen))) { - eth = skb_gro_header_slow(skb, hlen, 0); - if (unlikely(!eth)) { - net_warn_ratelimited("%s: dropping impossible skb from %s\n", - __func__, napi->dev->name); - napi_reuse_skb(napi, skb); - return NULL; - } - } else { - eth = (const struct ethhdr *)skb->data; - gro_pull_from_frag0(skb, hlen); - NAPI_GRO_CB(skb)->frag0 += hlen; - NAPI_GRO_CB(skb)->frag0_len -= hlen; - } - __skb_pull(skb, hlen); - - /* - * This works because the only protocols we care about don't require - * special handling. - * We'll fix it up properly in napi_frags_finish() - */ - skb->protocol = eth->h_proto; - - return skb; -} - -gro_result_t napi_gro_frags(struct napi_struct *napi) -{ - gro_result_t ret; - struct sk_buff *skb = napi_frags_skb(napi); - - trace_napi_gro_frags_entry(skb); - - ret = napi_frags_finish(napi, skb, dev_gro_receive(napi, skb)); - trace_napi_gro_frags_exit(ret); - - return ret; -} -EXPORT_SYMBOL(napi_gro_frags); - -/* Compute the checksum from gro_offset and return the folded value - * after adding in any pseudo checksum. - */ -__sum16 __skb_gro_checksum_complete(struct sk_buff *skb) -{ - __wsum wsum; - __sum16 sum; - - wsum = skb_checksum(skb, skb_gro_offset(skb), skb_gro_len(skb), 0); - - /* NAPI_GRO_CB(skb)->csum holds pseudo checksum */ - sum = csum_fold(csum_add(NAPI_GRO_CB(skb)->csum, wsum)); - /* See comments in __skb_checksum_complete(). */ - if (likely(!sum)) { - if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE) && - !skb->csum_complete_sw) - netdev_rx_csum_fault(skb->dev, skb); - } - - NAPI_GRO_CB(skb)->csum = wsum; - NAPI_GRO_CB(skb)->csum_valid = 1; - - return sum; -} -EXPORT_SYMBOL(__skb_gro_checksum_complete); - static void net_rps_send_ipi(struct softnet_data *remsd) { #ifdef CONFIG_RPS @@ -6446,7 +5922,7 @@ static int process_backlog(struct napi_struct *napi, int quota) net_rps_action_and_irq_enable(sd); } - napi->weight = dev_rx_weight; + napi->weight = READ_ONCE(dev_rx_weight); while (again) { struct sk_buff *skb; @@ -6460,8 +5936,7 @@ static int process_backlog(struct napi_struct *napi, int quota) } - local_irq_disable(); - rps_lock(sd); + rps_lock_irq_disable(sd); if (skb_queue_empty(&sd->input_pkt_queue)) { /* * Inline a custom version of __napi_complete(). @@ -6477,8 +5952,7 @@ static int process_backlog(struct napi_struct *napi, int quota) skb_queue_splice_tail_init(&sd->input_pkt_queue, &sd->process_queue); } - rps_unlock(sd); - local_irq_enable(); + rps_unlock_irq_enable(sd); } return work; @@ -6888,8 +6362,8 @@ int dev_set_threaded(struct net_device *dev, bool threaded) } EXPORT_SYMBOL(dev_set_threaded); -void netif_napi_add(struct net_device *dev, struct napi_struct *napi, - int (*poll)(struct napi_struct *, int), int weight) +void netif_napi_add_weight(struct net_device *dev, struct napi_struct *napi, + int (*poll)(struct napi_struct *, int), int weight) { if (WARN_ON(test_and_set_bit(NAPI_STATE_LISTED, &napi->state))) return; @@ -6915,6 +6389,7 @@ void netif_napi_add(struct net_device *dev, struct napi_struct *napi, set_bit(NAPI_STATE_NPSVC, &napi->state); list_add_rcu(&napi->dev_list, &dev->napi_list); napi_hash_add(napi); + napi_get_frags_check(napi); /* Create kthread for this napi if dev->threaded is set. * Clear dev->threaded if kthread creation failed so that * threaded mode will not be enabled in napi_enable(). @@ -6922,7 +6397,7 @@ void netif_napi_add(struct net_device *dev, struct napi_struct *napi, if (dev->threaded && napi_kthread_create(napi)) dev->threaded = 0; } -EXPORT_SYMBOL(netif_napi_add); +EXPORT_SYMBOL(netif_napi_add_weight); void napi_disable(struct napi_struct *n) { @@ -7151,12 +6626,34 @@ static int napi_threaded_poll(void *data) return 0; } +static void skb_defer_free_flush(struct softnet_data *sd) +{ + struct sk_buff *skb, *next; + unsigned long flags; + + /* Paired with WRITE_ONCE() in skb_attempt_defer_free() */ + if (!READ_ONCE(sd->defer_list)) + return; + + spin_lock_irqsave(&sd->defer_lock, flags); + skb = sd->defer_list; + sd->defer_list = NULL; + sd->defer_count = 0; + spin_unlock_irqrestore(&sd->defer_lock, flags); + + while (skb != NULL) { + next = skb->next; + napi_consume_skb(skb, 1); + skb = next; + } +} + static __latent_entropy void net_rx_action(struct softirq_action *h) { struct softnet_data *sd = this_cpu_ptr(&softnet_data); unsigned long time_limit = jiffies + - usecs_to_jiffies(netdev_budget_usecs); - int budget = netdev_budget; + usecs_to_jiffies(READ_ONCE(netdev_budget_usecs)); + int budget = READ_ONCE(netdev_budget); LIST_HEAD(list); LIST_HEAD(repoll); @@ -7167,9 +6664,11 @@ static __latent_entropy void net_rx_action(struct softirq_action *h) for (;;) { struct napi_struct *n; + skb_defer_free_flush(sd); + if (list_empty(&list)) { if (!sd_has_rps_ipi_waiting(sd) && list_empty(&repoll)) - return; + goto end; break; } @@ -7196,10 +6695,12 @@ static __latent_entropy void net_rx_action(struct softirq_action *h) __raise_softirq_irqoff(NET_RX_SOFTIRQ); net_rps_action_and_irq_enable(sd); +end:; } struct netdev_adjacent { struct net_device *dev; + netdevice_tracker dev_tracker; /* upper master flag, there can only be one master device per list */ bool master; @@ -7802,6 +7303,16 @@ static int __netdev_update_upper_level(struct net_device *dev, return 0; } +#ifdef CONFIG_LOCKDEP +static LIST_HEAD(net_unlink_list); + +static void net_unlink_todo(struct net_device *dev) +{ + if (list_empty(&dev->unlink_list)) + list_add_tail(&dev->unlink_list, &net_unlink_list); +} +#endif + static int __netdev_update_lower_level(struct net_device *dev, struct netdev_nested_priv *priv) { @@ -7964,7 +7475,7 @@ static int __netdev_adjacent_dev_insert(struct net_device *dev, adj->ref_nr = 1; adj->private = private; adj->ignore = false; - dev_hold(adj_dev); + netdev_hold(adj_dev, &adj->dev_tracker, GFP_KERNEL); pr_debug("Insert adjacency: dev %s adj_dev %s adj->ref_nr %d; dev_hold on %s\n", dev->name, adj_dev->name, adj->ref_nr, adj_dev->name); @@ -7993,8 +7504,8 @@ remove_symlinks: if (netdev_adjacent_is_neigh_list(dev, adj_dev, dev_list)) netdev_adjacent_sysfs_del(dev, adj_dev->name, dev_list); free_adj: + netdev_put(adj_dev, &adj->dev_tracker); kfree(adj); - dev_put(adj_dev); return ret; } @@ -8035,7 +7546,7 @@ static void __netdev_adjacent_dev_remove(struct net_device *dev, list_del_rcu(&adj->list); pr_debug("adjacency: dev_put for %s, because link removed from %s to %s\n", adj_dev->name, dev->name, adj_dev->name); - dev_put(adj_dev); + netdev_put(adj_dev, &adj->dev_tracker); kfree_rcu(adj, rcu); } @@ -8384,6 +7895,242 @@ void netdev_bonding_info_change(struct net_device *dev, } EXPORT_SYMBOL(netdev_bonding_info_change); +static int netdev_offload_xstats_enable_l3(struct net_device *dev, + struct netlink_ext_ack *extack) +{ + struct netdev_notifier_offload_xstats_info info = { + .info.dev = dev, + .info.extack = extack, + .type = NETDEV_OFFLOAD_XSTATS_TYPE_L3, + }; + int err; + int rc; + + dev->offload_xstats_l3 = kzalloc(sizeof(*dev->offload_xstats_l3), + GFP_KERNEL); + if (!dev->offload_xstats_l3) + return -ENOMEM; + + rc = call_netdevice_notifiers_info_robust(NETDEV_OFFLOAD_XSTATS_ENABLE, + NETDEV_OFFLOAD_XSTATS_DISABLE, + &info.info); + err = notifier_to_errno(rc); + if (err) + goto free_stats; + + return 0; + +free_stats: + kfree(dev->offload_xstats_l3); + dev->offload_xstats_l3 = NULL; + return err; +} + +int netdev_offload_xstats_enable(struct net_device *dev, + enum netdev_offload_xstats_type type, + struct netlink_ext_ack *extack) +{ + ASSERT_RTNL(); + + if (netdev_offload_xstats_enabled(dev, type)) + return -EALREADY; + + switch (type) { + case NETDEV_OFFLOAD_XSTATS_TYPE_L3: + return netdev_offload_xstats_enable_l3(dev, extack); + } + + WARN_ON(1); + return -EINVAL; +} +EXPORT_SYMBOL(netdev_offload_xstats_enable); + +static void netdev_offload_xstats_disable_l3(struct net_device *dev) +{ + struct netdev_notifier_offload_xstats_info info = { + .info.dev = dev, + .type = NETDEV_OFFLOAD_XSTATS_TYPE_L3, + }; + + call_netdevice_notifiers_info(NETDEV_OFFLOAD_XSTATS_DISABLE, + &info.info); + kfree(dev->offload_xstats_l3); + dev->offload_xstats_l3 = NULL; +} + +int netdev_offload_xstats_disable(struct net_device *dev, + enum netdev_offload_xstats_type type) +{ + ASSERT_RTNL(); + + if (!netdev_offload_xstats_enabled(dev, type)) + return -EALREADY; + + switch (type) { + case NETDEV_OFFLOAD_XSTATS_TYPE_L3: + netdev_offload_xstats_disable_l3(dev); + return 0; + } + + WARN_ON(1); + return -EINVAL; +} +EXPORT_SYMBOL(netdev_offload_xstats_disable); + +static void netdev_offload_xstats_disable_all(struct net_device *dev) +{ + netdev_offload_xstats_disable(dev, NETDEV_OFFLOAD_XSTATS_TYPE_L3); +} + +static struct rtnl_hw_stats64 * +netdev_offload_xstats_get_ptr(const struct net_device *dev, + enum netdev_offload_xstats_type type) +{ + switch (type) { + case NETDEV_OFFLOAD_XSTATS_TYPE_L3: + return dev->offload_xstats_l3; + } + + WARN_ON(1); + return NULL; +} + +bool netdev_offload_xstats_enabled(const struct net_device *dev, + enum netdev_offload_xstats_type type) +{ + ASSERT_RTNL(); + + return netdev_offload_xstats_get_ptr(dev, type); +} +EXPORT_SYMBOL(netdev_offload_xstats_enabled); + +struct netdev_notifier_offload_xstats_ru { + bool used; +}; + +struct netdev_notifier_offload_xstats_rd { + struct rtnl_hw_stats64 stats; + bool used; +}; + +static void netdev_hw_stats64_add(struct rtnl_hw_stats64 *dest, + const struct rtnl_hw_stats64 *src) +{ + dest->rx_packets += src->rx_packets; + dest->tx_packets += src->tx_packets; + dest->rx_bytes += src->rx_bytes; + dest->tx_bytes += src->tx_bytes; + dest->rx_errors += src->rx_errors; + dest->tx_errors += src->tx_errors; + dest->rx_dropped += src->rx_dropped; + dest->tx_dropped += src->tx_dropped; + dest->multicast += src->multicast; +} + +static int netdev_offload_xstats_get_used(struct net_device *dev, + enum netdev_offload_xstats_type type, + bool *p_used, + struct netlink_ext_ack *extack) +{ + struct netdev_notifier_offload_xstats_ru report_used = {}; + struct netdev_notifier_offload_xstats_info info = { + .info.dev = dev, + .info.extack = extack, + .type = type, + .report_used = &report_used, + }; + int rc; + + WARN_ON(!netdev_offload_xstats_enabled(dev, type)); + rc = call_netdevice_notifiers_info(NETDEV_OFFLOAD_XSTATS_REPORT_USED, + &info.info); + *p_used = report_used.used; + return notifier_to_errno(rc); +} + +static int netdev_offload_xstats_get_stats(struct net_device *dev, + enum netdev_offload_xstats_type type, + struct rtnl_hw_stats64 *p_stats, + bool *p_used, + struct netlink_ext_ack *extack) +{ + struct netdev_notifier_offload_xstats_rd report_delta = {}; + struct netdev_notifier_offload_xstats_info info = { + .info.dev = dev, + .info.extack = extack, + .type = type, + .report_delta = &report_delta, + }; + struct rtnl_hw_stats64 *stats; + int rc; + + stats = netdev_offload_xstats_get_ptr(dev, type); + if (WARN_ON(!stats)) + return -EINVAL; + + rc = call_netdevice_notifiers_info(NETDEV_OFFLOAD_XSTATS_REPORT_DELTA, + &info.info); + + /* Cache whatever we got, even if there was an error, otherwise the + * successful stats retrievals would get lost. + */ + netdev_hw_stats64_add(stats, &report_delta.stats); + + if (p_stats) + *p_stats = *stats; + *p_used = report_delta.used; + + return notifier_to_errno(rc); +} + +int netdev_offload_xstats_get(struct net_device *dev, + enum netdev_offload_xstats_type type, + struct rtnl_hw_stats64 *p_stats, bool *p_used, + struct netlink_ext_ack *extack) +{ + ASSERT_RTNL(); + + if (p_stats) + return netdev_offload_xstats_get_stats(dev, type, p_stats, + p_used, extack); + else + return netdev_offload_xstats_get_used(dev, type, p_used, + extack); +} +EXPORT_SYMBOL(netdev_offload_xstats_get); + +void +netdev_offload_xstats_report_delta(struct netdev_notifier_offload_xstats_rd *report_delta, + const struct rtnl_hw_stats64 *stats) +{ + report_delta->used = true; + netdev_hw_stats64_add(&report_delta->stats, stats); +} +EXPORT_SYMBOL(netdev_offload_xstats_report_delta); + +void +netdev_offload_xstats_report_used(struct netdev_notifier_offload_xstats_ru *report_used) +{ + report_used->used = true; +} +EXPORT_SYMBOL(netdev_offload_xstats_report_used); + +void netdev_offload_xstats_push_delta(struct net_device *dev, + enum netdev_offload_xstats_type type, + const struct rtnl_hw_stats64 *p_stats) +{ + struct rtnl_hw_stats64 *stats; + + ASSERT_RTNL(); + + stats = netdev_offload_xstats_get_ptr(dev, type); + if (WARN_ON(!stats)) + return; + + netdev_hw_stats64_add(stats, p_stats); +} +EXPORT_SYMBOL(netdev_offload_xstats_push_delta); + /** * netdev_get_xmit_slave - Get the xmit slave of master device * @dev: device @@ -9004,7 +8751,6 @@ void dev_set_group(struct net_device *dev, int new_group) { dev->group = new_group; } -EXPORT_SYMBOL(dev_set_group); /** * dev_pre_changeaddr_notify - Call NETDEV_PRE_CHANGEADDR. @@ -9119,7 +8865,6 @@ int dev_change_carrier(struct net_device *dev, bool new_carrier) return -ENODEV; return ops->ndo_change_carrier(dev, new_carrier); } -EXPORT_SYMBOL(dev_change_carrier); /** * dev_get_phys_port_id - Get device physical port ID @@ -9137,7 +8882,6 @@ int dev_get_phys_port_id(struct net_device *dev, return -EOPNOTSUPP; return ops->ndo_get_phys_port_id(dev, ppid); } -EXPORT_SYMBOL(dev_get_phys_port_id); /** * dev_get_phys_port_name - Get device physical port name @@ -9160,7 +8904,6 @@ int dev_get_phys_port_name(struct net_device *dev, } return devlink_compat_phys_port_name_get(dev, name, len); } -EXPORT_SYMBOL(dev_get_phys_port_name); /** * dev_get_port_parent_id - Get the device's port parent identifier @@ -9224,35 +8967,17 @@ 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 - update protocol port state information + * dev_change_proto_down - set carrier according to proto_down. + * * @dev: device * @proto_down: new value - * - * This info can be used by switch drivers to set the phys state of the - * port. */ int dev_change_proto_down(struct net_device *dev, bool proto_down) { - const struct net_device_ops *ops = dev->netdev_ops; - - if (!ops->ndo_change_proto_down) + if (!(dev->priv_flags & IFF_CHANGE_PROTO_DOWN)) return -EOPNOTSUPP; if (!netif_device_present(dev)) return -ENODEV; - return ops->ndo_change_proto_down(dev, proto_down); -} -EXPORT_SYMBOL(dev_change_proto_down); - -/** - * dev_change_proto_down_generic - generic implementation for - * ndo_change_proto_down that sets carrier according to - * proto_down. - * - * @dev: device - * @proto_down: new value - */ -int dev_change_proto_down_generic(struct net_device *dev, bool proto_down) -{ if (proto_down) netif_carrier_off(dev); else @@ -9260,7 +8985,6 @@ int dev_change_proto_down_generic(struct net_device *dev, bool proto_down) dev->proto_down = proto_down; return 0; } -EXPORT_SYMBOL(dev_change_proto_down_generic); /** * dev_change_proto_down_reason - proto down reason @@ -9285,7 +9009,6 @@ void dev_change_proto_down_reason(struct net_device *dev, unsigned long mask, } } } -EXPORT_SYMBOL(dev_change_proto_down_reason); struct bpf_xdp_link { struct bpf_link link; @@ -9656,6 +9379,12 @@ static int bpf_xdp_link_update(struct bpf_link *link, struct bpf_prog *new_prog, goto out_unlock; } old_prog = link->prog; + if (old_prog->type != new_prog->type || + old_prog->expected_attach_type != new_prog->expected_attach_type) { + err = -EINVAL; + goto out_unlock; + } + if (old_prog == new_prog) { /* no-op, don't disturb drivers */ bpf_prog_put(new_prog); @@ -9806,13 +9535,13 @@ static int dev_new_index(struct net *net) } /* Delayed registration/unregisteration */ -static LIST_HEAD(net_todo_list); +LIST_HEAD(net_todo_list); DECLARE_WAIT_QUEUE_HEAD(netdev_unregistering_wq); static void net_set_todo(struct net_device *dev) { list_add_tail(&dev->todo_list, &net_todo_list); - dev_net(dev)->dev_unreg_count++; + atomic_inc(&dev_net(dev)->dev_unreg_count); } static netdev_features_t netdev_sync_upper_features(struct net_device *lower, @@ -10213,22 +9942,14 @@ void netif_tx_stop_all_queues(struct net_device *dev) EXPORT_SYMBOL(netif_tx_stop_all_queues); /** - * register_netdevice - register a network device - * @dev: device to register - * - * Take a completed network device structure and add it to the kernel - * interfaces. A %NETDEV_REGISTER message is sent to the netdev notifier - * chain. 0 is returned on success. A negative errno code is returned - * on a failure to set up the device, or if the name is a duplicate. - * - * Callers must hold the rtnl semaphore. You may want - * register_netdev() instead of this. + * register_netdevice() - register a network device + * @dev: device to register * - * BUGS: - * The locking appears insufficient to guarantee two parallel registers - * will not get the same name. + * Take a prepared network device structure and make it externally accessible. + * A %NETDEV_REGISTER message is sent to the netdev notifier chain. + * Callers must hold the rtnl lock - you may want register_netdev() + * instead of this. */ - int register_netdevice(struct net_device *dev) { int ret; @@ -10334,11 +10055,11 @@ int register_netdevice(struct net_device *dev) goto err_uninit; ret = netdev_register_kobject(dev); - if (ret) { - dev->reg_state = NETREG_UNREGISTERED; + write_lock(&dev_base_lock); + dev->reg_state = ret ? NETREG_UNREGISTERED : NETREG_REGISTERED; + write_unlock(&dev_base_lock); + if (ret) goto err_uninit; - } - dev->reg_state = NETREG_REGISTERED; __netdev_update_features(dev); @@ -10352,8 +10073,10 @@ int register_netdevice(struct net_device *dev) linkwatch_init_dev(dev); dev_init_scheduler(dev); - dev_hold(dev); + + netdev_hold(dev, &dev->dev_registered_tracker, GFP_KERNEL); list_netdevice(dev); + add_device_randomness(dev->dev_addr, dev->addr_len); /* If the device has permanent device address, driver should @@ -10482,8 +10205,8 @@ int netdev_unregister_timeout_secs __read_mostly = 10; #define WAIT_REFS_MIN_MSECS 1 #define WAIT_REFS_MAX_MSECS 250 /** - * netdev_wait_allrefs - wait until all references are gone. - * @dev: target net_device + * netdev_wait_allrefs_any - wait until all references are gone. + * @list: list of net_devices to wait on * * This is called when unregistering network devices. * @@ -10493,37 +10216,42 @@ int netdev_unregister_timeout_secs __read_mostly = 10; * We can get stuck here if buggy protocols don't correctly * call dev_put. */ -static void netdev_wait_allrefs(struct net_device *dev) +static struct net_device *netdev_wait_allrefs_any(struct list_head *list) { unsigned long rebroadcast_time, warning_time; - int wait = 0, refcnt; - - linkwatch_forget_dev(dev); + struct net_device *dev; + int wait = 0; rebroadcast_time = warning_time = jiffies; - refcnt = netdev_refcnt_read(dev); - while (refcnt != 1) { + list_for_each_entry(dev, list, todo_list) + if (netdev_refcnt_read(dev) == 1) + return dev; + + while (true) { if (time_after(jiffies, rebroadcast_time + 1 * HZ)) { rtnl_lock(); /* Rebroadcast unregister notification */ - call_netdevice_notifiers(NETDEV_UNREGISTER, dev); + list_for_each_entry(dev, list, todo_list) + call_netdevice_notifiers(NETDEV_UNREGISTER, dev); __rtnl_unlock(); rcu_barrier(); rtnl_lock(); - if (test_bit(__LINK_STATE_LINKWATCH_PENDING, - &dev->state)) { - /* We must not have linkwatch events - * pending on unregister. If this - * happens, we simply run the queue - * unscheduled, resulting in a noop - * for this device. - */ - linkwatch_run_queue(); - } + list_for_each_entry(dev, list, todo_list) + if (test_bit(__LINK_STATE_LINKWATCH_PENDING, + &dev->state)) { + /* We must not have linkwatch events + * pending on unregister. If this + * happens, we simply run the queue + * unscheduled, resulting in a noop + * for this device. + */ + linkwatch_run_queue(); + break; + } __rtnl_unlock(); @@ -10538,13 +10266,18 @@ static void netdev_wait_allrefs(struct net_device *dev) wait = min(wait << 1, WAIT_REFS_MAX_MSECS); } - refcnt = netdev_refcnt_read(dev); + list_for_each_entry(dev, list, todo_list) + if (netdev_refcnt_read(dev) == 1) + return dev; + + if (time_after(jiffies, warning_time + + READ_ONCE(netdev_unregister_timeout_secs) * HZ)) { + list_for_each_entry(dev, list, todo_list) { + pr_emerg("unregister_netdevice: waiting for %s to become free. Usage count = %d\n", + dev->name, netdev_refcnt_read(dev)); + ref_tracker_dir_print(&dev->refcnt_tracker, 10); + } - if (refcnt != 1 && - time_after(jiffies, warning_time + - netdev_unregister_timeout_secs * HZ)) { - pr_emerg("unregister_netdevice: waiting for %s to become free. Usage count = %d\n", - dev->name, refcnt); warning_time = jiffies; } } @@ -10576,6 +10309,7 @@ static void netdev_wait_allrefs(struct net_device *dev) */ void netdev_run_todo(void) { + struct net_device *dev, *tmp; struct list_head list; #ifdef CONFIG_LOCKDEP struct list_head unlink_list; @@ -10596,26 +10330,26 @@ void netdev_run_todo(void) __rtnl_unlock(); - /* Wait for rcu callbacks to finish before next phase */ if (!list_empty(&list)) rcu_barrier(); - while (!list_empty(&list)) { - struct net_device *dev - = list_first_entry(&list, struct net_device, todo_list); - list_del(&dev->todo_list); - + list_for_each_entry_safe(dev, tmp, &list, todo_list) { if (unlikely(dev->reg_state != NETREG_UNREGISTERING)) { - pr_err("network todo '%s' but state %d\n", - dev->name, dev->reg_state); - dump_stack(); + netdev_WARN(dev, "run_todo but not unregistering\n"); + list_del(&dev->todo_list); continue; } + write_lock(&dev_base_lock); dev->reg_state = NETREG_UNREGISTERED; + write_unlock(&dev_base_lock); + linkwatch_forget_dev(dev); + } - netdev_wait_allrefs(dev); + while (!list_empty(&list)) { + dev = netdev_wait_allrefs_any(&list); + list_del(&dev->todo_list); /* paranoia */ BUG_ON(netdev_refcnt_read(dev) != 1); @@ -10623,19 +10357,14 @@ void netdev_run_todo(void) BUG_ON(!list_empty(&dev->ptype_specific)); WARN_ON(rcu_access_pointer(dev->ip_ptr)); WARN_ON(rcu_access_pointer(dev->ip6_ptr)); -#if IS_ENABLED(CONFIG_DECNET) - WARN_ON(dev->dn_ptr); -#endif + if (dev->priv_destructor) dev->priv_destructor(dev); if (dev->needs_free_netdev) free_netdev(dev); - /* Report a network device has been unregistered */ - rtnl_lock(); - dev_net(dev)->dev_unreg_count--; - __rtnl_unlock(); - wake_up(&netdev_unregistering_wq); + if (atomic_dec_and_test(&dev_net(dev)->dev_unreg_count)) + wake_up(&netdev_unregistering_wq); /* Free network device */ kobject_put(&dev->dev.kobj); @@ -10671,6 +10400,21 @@ void netdev_stats_to_stats64(struct rtnl_link_stats64 *stats64, } EXPORT_SYMBOL(netdev_stats_to_stats64); +struct net_device_core_stats __percpu *netdev_core_stats_alloc(struct net_device *dev) +{ + struct net_device_core_stats __percpu *p; + + p = alloc_percpu_gfp(struct net_device_core_stats, + GFP_ATOMIC | __GFP_NOWARN); + + if (p && cmpxchg(&dev->core_stats, NULL, p)) + free_percpu(p); + + /* This READ_ONCE() pairs with the cmpxchg() above */ + return READ_ONCE(dev->core_stats); +} +EXPORT_SYMBOL(netdev_core_stats_alloc); + /** * dev_get_stats - get network device statistics * @dev: device to get statistics from @@ -10685,6 +10429,7 @@ struct rtnl_link_stats64 *dev_get_stats(struct net_device *dev, struct rtnl_link_stats64 *storage) { const struct net_device_ops *ops = dev->netdev_ops; + const struct net_device_core_stats __percpu *p; if (ops->ndo_get_stats64) { memset(storage, 0, sizeof(*storage)); @@ -10694,9 +10439,21 @@ struct rtnl_link_stats64 *dev_get_stats(struct net_device *dev, } else { netdev_stats_to_stats64(storage, &dev->stats); } - storage->rx_dropped += (unsigned long)atomic_long_read(&dev->rx_dropped); - storage->tx_dropped += (unsigned long)atomic_long_read(&dev->tx_dropped); - storage->rx_nohandler += (unsigned long)atomic_long_read(&dev->rx_nohandler); + + /* This READ_ONCE() pairs with the write in netdev_core_stats_alloc() */ + p = READ_ONCE(dev->core_stats); + if (p) { + const struct net_device_core_stats *core_stats; + int i; + + for_each_possible_cpu(i) { + core_stats = per_cpu_ptr(p, i); + storage->rx_dropped += READ_ONCE(core_stats->rx_dropped); + storage->tx_dropped += READ_ONCE(core_stats->tx_dropped); + storage->rx_nohandler += READ_ONCE(core_stats->rx_nohandler); + storage->rx_otherhost_dropped += READ_ONCE(core_stats->rx_otherhost_dropped); + } + } return storage; } EXPORT_SYMBOL(dev_get_stats); @@ -10714,23 +10471,23 @@ void dev_fetch_sw_netstats(struct rtnl_link_stats64 *s, int cpu; for_each_possible_cpu(cpu) { + u64 rx_packets, rx_bytes, tx_packets, tx_bytes; const struct pcpu_sw_netstats *stats; - struct pcpu_sw_netstats tmp; unsigned int start; stats = per_cpu_ptr(netstats, cpu); do { start = u64_stats_fetch_begin_irq(&stats->syncp); - tmp.rx_packets = stats->rx_packets; - tmp.rx_bytes = stats->rx_bytes; - tmp.tx_packets = stats->tx_packets; - tmp.tx_bytes = stats->tx_bytes; + rx_packets = u64_stats_read(&stats->rx_packets); + rx_bytes = u64_stats_read(&stats->rx_bytes); + tx_packets = u64_stats_read(&stats->tx_packets); + tx_bytes = u64_stats_read(&stats->tx_bytes); } while (u64_stats_fetch_retry_irq(&stats->syncp, start)); - s->rx_packets += tmp.rx_packets; - s->rx_bytes += tmp.rx_bytes; - s->tx_packets += tmp.tx_packets; - s->tx_bytes += tmp.tx_bytes; + s->rx_packets += rx_packets; + s->rx_bytes += rx_bytes; + s->tx_packets += tx_packets; + s->tx_bytes += tx_bytes; } } EXPORT_SYMBOL_GPL(dev_fetch_sw_netstats); @@ -10835,11 +10592,12 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, dev = PTR_ALIGN(p, NETDEV_ALIGN); dev->padded = (char *)dev - (char *)p; + ref_tracker_dir_init(&dev->refcnt_tracker, 128); #ifdef CONFIG_PCPU_DEV_REFCNT dev->pcpu_refcnt = alloc_percpu(int); if (!dev->pcpu_refcnt) goto free_dev; - dev_hold(dev); + __dev_hold(dev); #else refcount_set(&dev->dev_refcnt, 1); #endif @@ -10852,8 +10610,11 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, dev_net_set(dev, &init_net); - dev->gso_max_size = GSO_MAX_SIZE; + dev->gso_max_size = GSO_LEGACY_MAX_SIZE; dev->gso_max_segs = GSO_MAX_SEGS; + dev->gro_max_size = GRO_LEGACY_MAX_SIZE; + dev->tso_max_size = TSO_LEGACY_MAX_SIZE; + dev->tso_max_segs = TSO_MAX_SEGS; dev->upper_level = 1; dev->lower_level = 1; #ifdef CONFIG_LOCKDEP @@ -10951,10 +10712,13 @@ void free_netdev(struct net_device *dev) list_for_each_entry_safe(p, n, &dev->napi_list, dev_list) netif_napi_del(p); + ref_tracker_dir_exit(&dev->refcnt_tracker); #ifdef CONFIG_PCPU_DEV_REFCNT free_percpu(dev->pcpu_refcnt); dev->pcpu_refcnt = NULL; #endif + free_percpu(dev->core_stats); + dev->core_stats = NULL; free_percpu(dev->xdp_bulkq); dev->xdp_bulkq = NULL; @@ -11058,9 +10822,10 @@ void unregister_netdevice_many(struct list_head *head) list_for_each_entry(dev, head, unreg_list) { /* And unlink it from device chain. */ - unlist_netdevice(dev); - + write_lock(&dev_base_lock); + unlist_netdevice(dev, false); dev->reg_state = NETREG_UNREGISTERING; + write_unlock(&dev_base_lock); } flush_all_backlogs(); @@ -11074,6 +10839,8 @@ void unregister_netdevice_many(struct list_head *head) dev_xdp_uninstall(dev); + netdev_offload_xstats_disable_all(dev); + /* Notify protocols, that we are about to destroy * this device. They should clean all the things. */ @@ -11114,7 +10881,7 @@ void unregister_netdevice_many(struct list_head *head) synchronize_net(); list_for_each_entry(dev, head, unreg_list) { - dev_put(dev); + netdev_put(dev, &dev->dev_registered_tracker); net_set_todo(dev); } @@ -11205,7 +10972,7 @@ int __dev_change_net_namespace(struct net_device *dev, struct net *net, dev_close(dev); /* And unlink it from device chain */ - unlist_netdevice(dev); + unlist_netdevice(dev, true); synchronize_net(); @@ -11339,11 +11106,11 @@ static int dev_cpu_dead(unsigned int oldcpu) /* Process offline CPU's input_pkt_queue */ while ((skb = __skb_dequeue(&oldsd->process_queue))) { - netif_rx_ni(skb); + netif_rx(skb); input_queue_head_incr(oldsd); } while ((skb = skb_dequeue(&oldsd->input_pkt_queue))) { - netif_rx_ni(skb); + netif_rx(skb); input_queue_head_incr(oldsd); } @@ -11397,8 +11164,7 @@ static int __net_init netdev_init(struct net *net) BUILD_BUG_ON(GRO_HASH_BUCKETS > 8 * sizeof_field(struct napi_struct, gro_bitmask)); - if (net != &init_net) - INIT_LIST_HEAD(&net->dev_base_head); + INIT_LIST_HEAD(&net->dev_base_head); net->dev_name_head = netdev_create_hash(); if (net->dev_name_head == NULL) @@ -11514,14 +11280,14 @@ static struct pernet_operations __net_initdata netdev_net_ops = { .exit = netdev_exit, }; -static void __net_exit default_device_exit(struct net *net) +static void __net_exit default_device_exit_net(struct net *net) { struct net_device *dev, *aux; /* * Push all migratable network devices back to the * initial network namespace */ - rtnl_lock(); + ASSERT_RTNL(); for_each_netdev_safe(net, dev, aux) { int err; char fb_name[IFNAMSIZ]; @@ -11545,35 +11311,6 @@ static void __net_exit default_device_exit(struct net *net) BUG(); } } - rtnl_unlock(); -} - -static void __net_exit rtnl_lock_unregistering(struct list_head *net_list) -{ - /* Return with the rtnl_lock held when there are no network - * devices unregistering in any network namespace in net_list. - */ - struct net *net; - bool unregistering; - DEFINE_WAIT_FUNC(wait, woken_wake_function); - - add_wait_queue(&netdev_unregistering_wq, &wait); - for (;;) { - unregistering = false; - rtnl_lock(); - list_for_each_entry(net, net_list, exit_list) { - if (net->dev_unreg_count > 0) { - unregistering = true; - break; - } - } - if (!unregistering) - break; - __rtnl_unlock(); - - wait_woken(&wait, TASK_UNINTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT); - } - remove_wait_queue(&netdev_unregistering_wq, &wait); } static void __net_exit default_device_exit_batch(struct list_head *net_list) @@ -11587,18 +11324,12 @@ static void __net_exit default_device_exit_batch(struct list_head *net_list) struct net *net; LIST_HEAD(dev_kill_list); - /* To prevent network device cleanup code from dereferencing - * loopback devices or network devices that have been freed - * wait here for all pending unregistrations to complete, - * before unregistring the loopback device and allowing the - * network namespace be freed. - * - * The netdev todo list containing all network devices - * unregistrations that happen in default_device_exit_batch - * will run in the rtnl_unlock() at the end of - * default_device_exit_batch. - */ - rtnl_lock_unregistering(net_list); + rtnl_lock(); + list_for_each_entry(net, net_list, exit_list) { + default_device_exit_net(net); + cond_resched(); + } + list_for_each_entry(net, net_list, exit_list) { for_each_netdev_reverse(net, dev) { if (dev->rtnl_link_ops && dev->rtnl_link_ops->dellink) @@ -11612,7 +11343,6 @@ static void __net_exit default_device_exit_batch(struct list_head *net_list) } static struct pernet_operations __net_initdata default_device_ops = { - .exit = default_device_exit, .exit_batch = default_device_exit_batch, }; @@ -11643,8 +11373,6 @@ static int __init net_dev_init(void) for (i = 0; i < PTYPE_HASH_SIZE; i++) INIT_LIST_HEAD(&ptype_base[i]); - INIT_LIST_HEAD(&offload_base); - if (register_pernet_subsys(&netdev_net_ops)) goto out; @@ -11669,6 +11397,8 @@ static int __init net_dev_init(void) INIT_CSD(&sd->csd, rps_trigger_softirq, sd); sd->cpu = i; #endif + INIT_CSD(&sd->defer_csd, trigger_rx_softirq, sd); + spin_lock_init(&sd->defer_lock); init_gro_hash(&sd->backlog); sd->backlog.poll = process_backlog; |