diff options
Diffstat (limited to 'net/core')
| -rw-r--r-- | net/core/Makefile | 1 | ||||
| -rw-r--r-- | net/core/dev.c | 431 | ||||
| -rw-r--r-- | net/core/devlink.c | 50 | ||||
| -rw-r--r-- | net/core/dst.c | 1 | ||||
| -rw-r--r-- | net/core/ethtool.c | 40 | ||||
| -rw-r--r-- | net/core/filter.c | 270 | ||||
| -rw-r--r-- | net/core/flow_dissector.c | 57 | ||||
| -rw-r--r-- | net/core/gro_cells.c | 92 | ||||
| -rw-r--r-- | net/core/lwt_bpf.c | 4 | ||||
| -rw-r--r-- | net/core/lwtunnel.c | 4 | ||||
| -rw-r--r-- | net/core/netprio_cgroup.c | 1 | ||||
| -rw-r--r-- | net/core/pktgen.c | 4 | ||||
| -rw-r--r-- | net/core/request_sock.c | 2 | ||||
| -rw-r--r-- | net/core/rtnetlink.c | 78 | ||||
| -rw-r--r-- | net/core/scm.c | 2 | ||||
| -rw-r--r-- | net/core/secure_seq.c | 147 | ||||
| -rw-r--r-- | net/core/skbuff.c | 20 | ||||
| -rw-r--r-- | net/core/sock.c | 21 | ||||
| -rw-r--r-- | net/core/sysctl_net_core.c | 38 |
19 files changed, 724 insertions, 539 deletions
diff --git a/net/core/Makefile b/net/core/Makefile index f6761b6e3b29..79f9479e9658 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -28,3 +28,4 @@ obj-$(CONFIG_LWTUNNEL_BPF) += lwt_bpf.o obj-$(CONFIG_DST_CACHE) += dst_cache.o obj-$(CONFIG_HWBM) += hwbm.o obj-$(CONFIG_NET_DEVLINK) += devlink.o +obj-$(CONFIG_GRO_CELLS) += gro_cells.o diff --git a/net/core/dev.c b/net/core/dev.c index 29101c98399f..304f2deae5f9 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1,5 +1,5 @@ /* - * NET3 Protocol independent device support routines. + * NET3 Protocol independent device support routines. * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License @@ -7,7 +7,7 @@ * 2 of the License, or (at your option) any later version. * * Derived from the non IP parts of dev.c 1.0.19 - * Authors: Ross Biro + * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * Mark Evans, <evansmp@uhura.aston.ac.uk> * @@ -21,9 +21,9 @@ * * Changes: * D.J. Barrow : Fixed bug where dev->refcnt gets set - * to 2 if register_netdev gets called - * before net_dev_init & also removed a - * few lines of code in the process. + * to 2 if register_netdev gets called + * before net_dev_init & also removed a + * few lines of code in the process. * Alan Cox : device private ioctl copies fields back. * Alan Cox : Transmit queue code does relevant * stunts to keep the queue safe. @@ -36,7 +36,7 @@ * Alan Cox : 100 backlog just doesn't cut it when * you start doing multicast video 8) * Alan Cox : Rewrote net_bh and list manager. - * Alan Cox : Fix ETH_P_ALL echoback lengths. + * Alan Cox : Fix ETH_P_ALL echoback lengths. * Alan Cox : Took out transmit every packet pass * Saved a few bytes in the ioctl handler * Alan Cox : Network driver sets packet type before @@ -46,7 +46,7 @@ * Richard Kooijman: Timestamp fixes. * Alan Cox : Wrong field in SIOCGIFDSTADDR * Alan Cox : Device lock protection. - * Alan Cox : Fixed nasty side effect of device close + * Alan Cox : Fixed nasty side effect of device close * changes. * Rudi Cilibrasi : Pass the right thing to * set_mac_address() @@ -67,8 +67,8 @@ * Paul Rusty Russell : SIOCSIFNAME * Pekka Riikonen : Netdev boot-time settings code * Andrew Morton : Make unregister_netdevice wait - * indefinitely on dev->refcnt - * J Hadi Salim : - Backlog queue sampling + * indefinitely on dev->refcnt + * J Hadi Salim : - Backlog queue sampling * - netif_rx() feedback */ @@ -192,7 +192,8 @@ static seqcount_t devnet_rename_seq; static inline void dev_base_seq_inc(struct net *net) { - while (++net->dev_base_seq == 0); + while (++net->dev_base_seq == 0) + ; } static inline struct hlist_head *dev_name_hash(struct net *net, const char *name) @@ -274,8 +275,8 @@ EXPORT_PER_CPU_SYMBOL(softnet_data); * register_netdevice() inits txq->_xmit_lock and sets lockdep class * according to dev->type */ -static const unsigned short netdev_lock_type[] = - {ARPHRD_NETROM, ARPHRD_ETHER, ARPHRD_EETHER, ARPHRD_AX25, +static const unsigned short netdev_lock_type[] = { + ARPHRD_NETROM, ARPHRD_ETHER, ARPHRD_EETHER, ARPHRD_AX25, ARPHRD_PRONET, ARPHRD_CHAOS, ARPHRD_IEEE802, ARPHRD_ARCNET, ARPHRD_APPLETLK, ARPHRD_DLCI, ARPHRD_ATM, ARPHRD_METRICOM, ARPHRD_IEEE1394, ARPHRD_EUI64, ARPHRD_INFINIBAND, ARPHRD_SLIP, @@ -291,22 +292,22 @@ static const unsigned short netdev_lock_type[] = ARPHRD_IEEE80211_RADIOTAP, ARPHRD_PHONET, ARPHRD_PHONET_PIPE, ARPHRD_IEEE802154, ARPHRD_VOID, ARPHRD_NONE}; -static const char *const netdev_lock_name[] = - {"_xmit_NETROM", "_xmit_ETHER", "_xmit_EETHER", "_xmit_AX25", - "_xmit_PRONET", "_xmit_CHAOS", "_xmit_IEEE802", "_xmit_ARCNET", - "_xmit_APPLETLK", "_xmit_DLCI", "_xmit_ATM", "_xmit_METRICOM", - "_xmit_IEEE1394", "_xmit_EUI64", "_xmit_INFINIBAND", "_xmit_SLIP", - "_xmit_CSLIP", "_xmit_SLIP6", "_xmit_CSLIP6", "_xmit_RSRVD", - "_xmit_ADAPT", "_xmit_ROSE", "_xmit_X25", "_xmit_HWX25", - "_xmit_PPP", "_xmit_CISCO", "_xmit_LAPB", "_xmit_DDCMP", - "_xmit_RAWHDLC", "_xmit_TUNNEL", "_xmit_TUNNEL6", "_xmit_FRAD", - "_xmit_SKIP", "_xmit_LOOPBACK", "_xmit_LOCALTLK", "_xmit_FDDI", - "_xmit_BIF", "_xmit_SIT", "_xmit_IPDDP", "_xmit_IPGRE", - "_xmit_PIMREG", "_xmit_HIPPI", "_xmit_ASH", "_xmit_ECONET", - "_xmit_IRDA", "_xmit_FCPP", "_xmit_FCAL", "_xmit_FCPL", - "_xmit_FCFABRIC", "_xmit_IEEE80211", "_xmit_IEEE80211_PRISM", - "_xmit_IEEE80211_RADIOTAP", "_xmit_PHONET", "_xmit_PHONET_PIPE", - "_xmit_IEEE802154", "_xmit_VOID", "_xmit_NONE"}; +static const char *const netdev_lock_name[] = { + "_xmit_NETROM", "_xmit_ETHER", "_xmit_EETHER", "_xmit_AX25", + "_xmit_PRONET", "_xmit_CHAOS", "_xmit_IEEE802", "_xmit_ARCNET", + "_xmit_APPLETLK", "_xmit_DLCI", "_xmit_ATM", "_xmit_METRICOM", + "_xmit_IEEE1394", "_xmit_EUI64", "_xmit_INFINIBAND", "_xmit_SLIP", + "_xmit_CSLIP", "_xmit_SLIP6", "_xmit_CSLIP6", "_xmit_RSRVD", + "_xmit_ADAPT", "_xmit_ROSE", "_xmit_X25", "_xmit_HWX25", + "_xmit_PPP", "_xmit_CISCO", "_xmit_LAPB", "_xmit_DDCMP", + "_xmit_RAWHDLC", "_xmit_TUNNEL", "_xmit_TUNNEL6", "_xmit_FRAD", + "_xmit_SKIP", "_xmit_LOOPBACK", "_xmit_LOCALTLK", "_xmit_FDDI", + "_xmit_BIF", "_xmit_SIT", "_xmit_IPDDP", "_xmit_IPGRE", + "_xmit_PIMREG", "_xmit_HIPPI", "_xmit_ASH", "_xmit_ECONET", + "_xmit_IRDA", "_xmit_FCPP", "_xmit_FCAL", "_xmit_FCPL", + "_xmit_FCFABRIC", "_xmit_IEEE80211", "_xmit_IEEE80211_PRISM", + "_xmit_IEEE80211_RADIOTAP", "_xmit_PHONET", "_xmit_PHONET_PIPE", + "_xmit_IEEE802154", "_xmit_VOID", "_xmit_NONE"}; static struct lock_class_key netdev_xmit_lock_key[ARRAY_SIZE(netdev_lock_type)]; static struct lock_class_key netdev_addr_lock_key[ARRAY_SIZE(netdev_lock_type)]; @@ -352,10 +353,11 @@ static inline void netdev_set_addr_lockdep_class(struct net_device *dev) #endif /******************************************************************************* + * + * Protocol management and registration routines + * + *******************************************************************************/ - Protocol management and registration routines - -*******************************************************************************/ /* * Add a protocol ID to the list. Now that the input handler is @@ -538,10 +540,10 @@ void dev_remove_offload(struct packet_offload *po) EXPORT_SYMBOL(dev_remove_offload); /****************************************************************************** - - Device Boot-time Settings Routines - -*******************************************************************************/ + * + * Device Boot-time Settings Routines + * + ******************************************************************************/ /* Boot time configuration table */ static struct netdev_boot_setup dev_boot_setup[NETDEV_BOOT_SETUP_MAX]; @@ -574,13 +576,13 @@ static int netdev_boot_setup_add(char *name, struct ifmap *map) } /** - * netdev_boot_setup_check - check boot time settings - * @dev: the netdevice + * netdev_boot_setup_check - check boot time settings + * @dev: the netdevice * - * Check boot time settings for the device. - * The found settings are set for the device to be used - * later in the device probing. - * Returns 0 if no settings found, 1 if they are. + * Check boot time settings for the device. + * The found settings are set for the device to be used + * later in the device probing. + * Returns 0 if no settings found, 1 if they are. */ int netdev_boot_setup_check(struct net_device *dev) { @@ -590,10 +592,10 @@ int netdev_boot_setup_check(struct net_device *dev) for (i = 0; i < NETDEV_BOOT_SETUP_MAX; i++) { if (s[i].name[0] != '\0' && s[i].name[0] != ' ' && !strcmp(dev->name, s[i].name)) { - dev->irq = s[i].map.irq; - dev->base_addr = s[i].map.base_addr; - dev->mem_start = s[i].map.mem_start; - dev->mem_end = s[i].map.mem_end; + dev->irq = s[i].map.irq; + dev->base_addr = s[i].map.base_addr; + dev->mem_start = s[i].map.mem_start; + dev->mem_end = s[i].map.mem_end; return 1; } } @@ -603,14 +605,14 @@ EXPORT_SYMBOL(netdev_boot_setup_check); /** - * netdev_boot_base - get address from boot time settings - * @prefix: prefix for network device - * @unit: id for network device + * netdev_boot_base - get address from boot time settings + * @prefix: prefix for network device + * @unit: id for network device * - * Check boot time settings for the base address of device. - * The found settings are set for the device to be used - * later in the device probing. - * Returns 0 if no settings found. + * Check boot time settings for the base address of device. + * The found settings are set for the device to be used + * later in the device probing. + * Returns 0 if no settings found. */ unsigned long netdev_boot_base(const char *prefix, int unit) { @@ -663,10 +665,10 @@ int __init netdev_boot_setup(char *str) __setup("netdev=", netdev_boot_setup); /******************************************************************************* - - Device Interface Subroutines - -*******************************************************************************/ + * + * Device Interface Subroutines + * + *******************************************************************************/ /** * dev_get_iflink - get 'iflink' value of a interface @@ -737,15 +739,15 @@ struct net_device *__dev_get_by_name(struct net *net, const char *name) EXPORT_SYMBOL(__dev_get_by_name); /** - * dev_get_by_name_rcu - find a device by its name - * @net: the applicable net namespace - * @name: name to find + * dev_get_by_name_rcu - find a device by its name + * @net: the applicable net namespace + * @name: name to find * - * Find an interface by name. - * If the name is found a pointer to the device is returned. - * If the name is not found then %NULL is returned. - * The reference counters are not incremented so the caller must be - * careful with locks. The caller must hold RCU lock. + * Find an interface by name. + * If the name is found a pointer to the device is returned. + * If the name is not found then %NULL is returned. + * The reference counters are not incremented so the caller must be + * careful with locks. The caller must hold RCU lock. */ struct net_device *dev_get_by_name_rcu(struct net *net, const char *name) @@ -1289,8 +1291,8 @@ void netdev_state_change(struct net_device *dev) EXPORT_SYMBOL(netdev_state_change); /** - * netdev_notify_peers - notify network peers about existence of @dev - * @dev: network device + * netdev_notify_peers - notify network peers about existence of @dev + * @dev: network device * * Generate traffic such that interested network peers are aware of * @dev, such as by generating a gratuitous ARP. This may be used when @@ -1518,17 +1520,17 @@ static int call_netdevice_notifier(struct notifier_block *nb, unsigned long val, static int dev_boot_phase = 1; /** - * register_netdevice_notifier - register a network notifier block - * @nb: notifier + * register_netdevice_notifier - register a network notifier block + * @nb: notifier * - * Register a notifier to be called when network device events occur. - * The notifier passed is linked into the kernel structures and must - * not be reused until it has been unregistered. A negative errno code - * is returned on a failure. + * Register a notifier to be called when network device events occur. + * The notifier passed is linked into the kernel structures and must + * not be reused until it has been unregistered. A negative errno code + * is returned on a failure. * - * When registered all registration and up events are replayed - * to the new notifier to allow device to have a race free - * view of the network device list. + * When registered all registration and up events are replayed + * to the new notifier to allow device to have a race free + * view of the network device list. */ int register_netdevice_notifier(struct notifier_block *nb) @@ -1585,17 +1587,17 @@ outroll: EXPORT_SYMBOL(register_netdevice_notifier); /** - * unregister_netdevice_notifier - unregister a network notifier block - * @nb: notifier + * unregister_netdevice_notifier - unregister a network notifier block + * @nb: notifier * - * Unregister a notifier previously registered by - * register_netdevice_notifier(). The notifier is unlinked into the - * kernel structures and may then be reused. A negative errno code - * is returned on a failure. + * Unregister a notifier previously registered by + * register_netdevice_notifier(). The notifier is unlinked into the + * kernel structures and may then be reused. A negative errno code + * is returned on a failure. * - * After unregistering unregister and down device events are synthesized - * for all devices on the device list to the removed notifier to remove - * the need for special case cleanup code. + * After unregistering unregister and down device events are synthesized + * for all devices on the device list to the removed notifier to remove + * the need for special case cleanup code. */ int unregister_netdevice_notifier(struct notifier_block *nb) @@ -2403,28 +2405,6 @@ void netif_schedule_queue(struct netdev_queue *txq) } EXPORT_SYMBOL(netif_schedule_queue); -/** - * netif_wake_subqueue - allow sending packets on subqueue - * @dev: network device - * @queue_index: sub queue index - * - * Resume individual transmit queue of a device with multiple transmit queues. - */ -void netif_wake_subqueue(struct net_device *dev, u16 queue_index) -{ - struct netdev_queue *txq = netdev_get_tx_queue(dev, queue_index); - - if (test_and_clear_bit(__QUEUE_STATE_DRV_XOFF, &txq->state)) { - struct Qdisc *q; - - rcu_read_lock(); - q = rcu_dereference(txq->qdisc); - __netif_schedule(q); - rcu_read_unlock(); - } -} -EXPORT_SYMBOL(netif_wake_subqueue); - void netif_tx_wake_queue(struct netdev_queue *dev_queue) { if (test_and_clear_bit(__QUEUE_STATE_DRV_XOFF, &dev_queue->state)) { @@ -2518,6 +2498,7 @@ u16 __skb_tx_hash(const struct net_device *dev, struct sk_buff *skb, if (dev->num_tc) { u8 tc = netdev_get_prio_tc_map(dev, skb->priority); + qoffset = dev->tc_to_txq[tc].offset; qcount = dev->tc_to_txq[tc].count; } @@ -2654,9 +2635,10 @@ EXPORT_SYMBOL(skb_mac_gso_segment); static inline bool skb_needs_check(struct sk_buff *skb, bool tx_path) { if (tx_path) - return skb->ip_summed != CHECKSUM_PARTIAL; - else - return skb->ip_summed == CHECKSUM_NONE; + return skb->ip_summed != CHECKSUM_PARTIAL && + skb->ip_summed != CHECKSUM_NONE; + + return skb->ip_summed == CHECKSUM_NONE; } /** @@ -2675,11 +2657,12 @@ static inline bool skb_needs_check(struct sk_buff *skb, bool tx_path) struct sk_buff *__skb_gso_segment(struct sk_buff *skb, netdev_features_t features, bool tx_path) { + struct sk_buff *segs; + if (unlikely(skb_needs_check(skb, tx_path))) { int err; - skb_warn_bad_offload(skb); - + /* We're going to init ->check field in TCP or UDP header */ err = skb_cow_head(skb, 0); if (err < 0) return ERR_PTR(err); @@ -2707,7 +2690,12 @@ struct sk_buff *__skb_gso_segment(struct sk_buff *skb, skb_reset_mac_header(skb); skb_reset_mac_len(skb); - return skb_mac_gso_segment(skb, features); + segs = skb_mac_gso_segment(skb, features); + + if (unlikely(skb_needs_check(skb, tx_path))) + skb_warn_bad_offload(skb); + + return segs; } EXPORT_SYMBOL(__skb_gso_segment); @@ -2732,9 +2720,11 @@ static int illegal_highdma(struct net_device *dev, struct sk_buff *skb) { #ifdef CONFIG_HIGHMEM int i; + if (!(dev->features & NETIF_F_HIGHDMA)) { for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; + if (PageHighMem(skb_frag_page(frag))) return 1; } @@ -2748,6 +2738,7 @@ static int illegal_highdma(struct net_device *dev, struct sk_buff *skb) for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; dma_addr_t addr = page_to_phys(skb_frag_page(frag)); + if (!pdev->dma_mask || addr + PAGE_SIZE - 1 > *pdev->dma_mask) return 1; } @@ -3148,9 +3139,7 @@ sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev) if (!cl) return skb; - /* skb->tc_verd and qdisc_skb_cb(skb)->pkt_len were already set - * earlier by the caller. - */ + /* qdisc_skb_cb(skb)->pkt_len was already set by the caller. */ qdisc_bstats_cpu_update(cl->q, skb); switch (tc_classify(skb, cl, &cl_res, false)) { @@ -3225,6 +3214,7 @@ static u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb) if (queue_index < 0 || skb->ooo_okay || queue_index >= dev->real_num_tx_queues) { int new_index = get_xps_queue(dev, skb); + if (new_index < 0) new_index = skb_tx_hash(dev, skb); @@ -3254,6 +3244,7 @@ struct netdev_queue *netdev_pick_tx(struct net_device *dev, if (dev->real_num_tx_queues != 1) { const struct net_device_ops *ops = dev->netdev_ops; + if (ops->ndo_select_queue) queue_index = ops->ndo_select_queue(dev, skb, accel_priv, __netdev_pick_tx); @@ -3315,7 +3306,7 @@ static int __dev_queue_xmit(struct sk_buff *skb, void *accel_priv) qdisc_pkt_len_init(skb); #ifdef CONFIG_NET_CLS_ACT - skb->tc_verd = SET_TC_AT(skb->tc_verd, AT_EGRESS); + skb->tc_at_ingress = 0; # ifdef CONFIG_NET_EGRESS if (static_key_false(&egress_needed)) { skb = sch_handle_egress(skb, &rc, dev); @@ -3342,16 +3333,16 @@ static int __dev_queue_xmit(struct sk_buff *skb, void *accel_priv) } /* The device has no queue. Common case for software devices: - loopback, all the sorts of tunnels... + * loopback, all the sorts of tunnels... - Really, it is unlikely that netif_tx_lock protection is necessary - here. (f.e. loopback and IP tunnels are clean ignoring statistics - counters.) - However, it is possible, that they rely on protection - made by us here. + * Really, it is unlikely that netif_tx_lock protection is necessary + * here. (f.e. loopback and IP tunnels are clean ignoring statistics + * counters.) + * However, it is possible, that they rely on protection + * made by us here. - Check this and shot the lock. It is not prone from deadlocks. - Either shot noqueue qdisc, it is even simpler 8) + * Check this and shot the lock. It is not prone from deadlocks. + *Either shot noqueue qdisc, it is even simpler 8) */ if (dev->flags & IFF_UP) { int cpu = smp_processor_id(); /* ok because BHs are off */ @@ -3413,16 +3404,20 @@ int dev_queue_xmit_accel(struct sk_buff *skb, void *accel_priv) EXPORT_SYMBOL(dev_queue_xmit_accel); -/*======================================================================= - Receiver routines - =======================================================================*/ +/************************************************************************* + * Receiver routines + *************************************************************************/ int netdev_max_backlog __read_mostly = 1000; EXPORT_SYMBOL(netdev_max_backlog); int netdev_tstamp_prequeue __read_mostly = 1; int netdev_budget __read_mostly = 300; -int weight_p __read_mostly = 64; /* old backlog weight */ +int weight_p __read_mostly = 64; /* old backlog weight */ +int dev_weight_rx_bias __read_mostly = 1; /* bias for backlog weight */ +int dev_weight_tx_bias __read_mostly = 1; /* bias for output_queue quota */ +int dev_rx_weight __read_mostly = 64; +int dev_tx_weight __read_mostly = 64; /* Called with irq disabled */ static inline void ____napi_schedule(struct softnet_data *sd, @@ -3779,6 +3774,7 @@ static int netif_rx_internal(struct sk_buff *skb) #endif { unsigned int qtail; + ret = enqueue_to_backlog(skb, get_cpu(), &qtail); put_cpu(); } @@ -3838,6 +3834,7 @@ static __latent_entropy void net_tx_action(struct softirq_action *h) while (clist) { struct sk_buff *skb = clist; + clist = clist->next; WARN_ON(atomic_read(&skb->users)); @@ -3911,7 +3908,7 @@ sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret, } qdisc_skb_cb(skb)->pkt_len = skb->len; - skb->tc_verd = SET_TC_AT(skb->tc_verd, AT_INGRESS); + skb->tc_at_ingress = 1; qdisc_bstats_cpu_update(cl->q, skb); switch (tc_classify(skb, cl, &cl_res, false)) { @@ -3976,9 +3973,7 @@ int netdev_rx_handler_register(struct net_device *dev, rx_handler_func_t *rx_handler, void *rx_handler_data) { - ASSERT_RTNL(); - - if (dev->rx_handler) + if (netdev_is_rx_handler_busy(dev)) return -EBUSY; /* Note: rx_handler_data must be set before rx_handler */ @@ -4084,12 +4079,8 @@ another_round: goto out; } -#ifdef CONFIG_NET_CLS_ACT - if (skb->tc_verd & TC_NCLS) { - skb->tc_verd = CLR_TC_NCLS(skb->tc_verd); - goto ncls; - } -#endif + if (skb_skip_tc_classify(skb)) + goto skip_classify; if (pfmemalloc) goto skip_taps; @@ -4117,10 +4108,8 @@ skip_taps: goto out; } #endif -#ifdef CONFIG_NET_CLS_ACT - skb->tc_verd = 0; -ncls: -#endif + skb_reset_tc(skb); +skip_classify: if (pfmemalloc && !skb_pfmemalloc_protocol(skb)) goto drop; @@ -4521,6 +4510,11 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff if (&ptype->list == head) goto normal; + if (IS_ERR(pp) && 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; @@ -4616,6 +4610,7 @@ static gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb) case GRO_MERGED_FREE: if (NAPI_GRO_CB(skb)->free == NAPI_GRO_FREE_STOLEN_HEAD) { skb_dst_drop(skb); + secpath_reset(skb); kmem_cache_free(skbuff_head_cache, skb); } else { __kfree_skb(skb); @@ -4624,6 +4619,7 @@ static gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb) case GRO_HELD: case GRO_MERGED: + case GRO_CONSUMED: break; } @@ -4656,6 +4652,7 @@ static void napi_reuse_skb(struct napi_struct *napi, struct sk_buff *skb) skb->encapsulation = 0; skb_shinfo(skb)->gso_type = 0; skb->truesize = SKB_TRUESIZE(skb_end_offset(skb)); + secpath_reset(skb); napi->skb = skb; } @@ -4694,6 +4691,7 @@ static gro_result_t napi_frags_finish(struct napi_struct *napi, break; case GRO_MERGED: + case GRO_CONSUMED: break; } @@ -4830,7 +4828,7 @@ static int process_backlog(struct napi_struct *napi, int quota) net_rps_action_and_irq_enable(sd); } - napi->weight = weight_p; + napi->weight = dev_rx_weight; while (again) { struct sk_buff *skb; @@ -4897,23 +4895,6 @@ void __napi_schedule_irqoff(struct napi_struct *n) } EXPORT_SYMBOL(__napi_schedule_irqoff); -bool __napi_complete(struct napi_struct *n) -{ - BUG_ON(!test_bit(NAPI_STATE_SCHED, &n->state)); - - /* Some drivers call us directly, instead of calling - * napi_complete_done(). - */ - if (unlikely(test_bit(NAPI_STATE_IN_BUSY_POLL, &n->state))) - return false; - - list_del_init(&n->poll_list); - smp_mb__before_atomic(); - clear_bit(NAPI_STATE_SCHED, &n->state); - return true; -} -EXPORT_SYMBOL(__napi_complete); - bool napi_complete_done(struct napi_struct *n, int work_done) { unsigned long flags; @@ -4940,14 +4921,13 @@ bool napi_complete_done(struct napi_struct *n, int work_done) else napi_gro_flush(n, false); } - if (likely(list_empty(&n->poll_list))) { - WARN_ON_ONCE(!test_and_clear_bit(NAPI_STATE_SCHED, &n->state)); - } else { + if (unlikely(!list_empty(&n->poll_list))) { /* If n->poll_list is not empty, we need to mask irqs */ local_irq_save(flags); - __napi_complete(n); + list_del_init(&n->poll_list); local_irq_restore(flags); } + WARN_ON_ONCE(!test_and_clear_bit(NAPI_STATE_SCHED, &n->state)); return true; } EXPORT_SYMBOL(napi_complete_done); @@ -4993,7 +4973,6 @@ bool sk_busy_loop(struct sock *sk, int nonblock) { unsigned long end_time = !nonblock ? sk_busy_loop_end_time(sk) : 0; int (*napi_poll)(struct napi_struct *napi, int budget); - int (*busy_poll)(struct napi_struct *dev); void *have_poll_lock = NULL; struct napi_struct *napi; int rc; @@ -5008,17 +4987,10 @@ restart: if (!napi) goto out; - /* Note: ndo_busy_poll method is optional in linux-4.5 */ - busy_poll = napi->dev->netdev_ops->ndo_busy_poll; - preempt_disable(); for (;;) { rc = 0; local_bh_disable(); - if (busy_poll) { - rc = busy_poll(napi); - goto count; - } if (!napi_poll) { unsigned long val = READ_ONCE(napi->state); @@ -5043,9 +5015,6 @@ count: LINUX_MIB_BUSYPOLLRXPACKETS, rc); local_bh_enable(); - if (rc == LL_FLUSH_FAILED) - break; /* permanent failure */ - if (nonblock || !skb_queue_empty(&sk->sk_receive_queue) || busy_loop_timeout(end_time)) break; @@ -5120,7 +5089,7 @@ static enum hrtimer_restart napi_watchdog(struct hrtimer *timer) napi = container_of(timer, struct napi_struct, timer); if (napi->gro_list) - napi_schedule(napi); + napi_schedule_irqoff(napi); return HRTIMER_NORESTART; } @@ -5706,6 +5675,7 @@ static int netdev_adjacent_sysfs_add(struct net_device *dev, struct list_head *dev_list) { char linkname[IFNAMSIZ+7]; + sprintf(linkname, dev_list == &dev->adj_list.upper ? "upper_%s" : "lower_%s", adj_dev->name); return sysfs_create_link(&(dev->dev.kobj), &(adj_dev->dev.kobj), @@ -5716,6 +5686,7 @@ static void netdev_adjacent_sysfs_del(struct net_device *dev, struct list_head *dev_list) { char linkname[IFNAMSIZ+7]; + sprintf(linkname, dev_list == &dev->adj_list.upper ? "upper_%s" : "lower_%s", name); sysfs_remove_link(&(dev->dev.kobj), linkname); @@ -5985,6 +5956,7 @@ void netdev_upper_dev_unlink(struct net_device *dev, struct net_device *upper_dev) { struct netdev_notifier_changeupper_info changeupper_info; + ASSERT_RTNL(); changeupper_info.upper_dev = upper_dev; @@ -6151,50 +6123,6 @@ void netdev_lower_state_changed(struct net_device *lower_dev, } EXPORT_SYMBOL(netdev_lower_state_changed); -int netdev_default_l2upper_neigh_construct(struct net_device *dev, - struct neighbour *n) -{ - struct net_device *lower_dev, *stop_dev; - struct list_head *iter; - int err; - - netdev_for_each_lower_dev(dev, lower_dev, iter) { - if (!lower_dev->netdev_ops->ndo_neigh_construct) - continue; - err = lower_dev->netdev_ops->ndo_neigh_construct(lower_dev, n); - if (err) { - stop_dev = lower_dev; - goto rollback; - } - } - return 0; - -rollback: - netdev_for_each_lower_dev(dev, lower_dev, iter) { - if (lower_dev == stop_dev) - break; - if (!lower_dev->netdev_ops->ndo_neigh_destroy) - continue; - lower_dev->netdev_ops->ndo_neigh_destroy(lower_dev, n); - } - return err; -} -EXPORT_SYMBOL_GPL(netdev_default_l2upper_neigh_construct); - -void netdev_default_l2upper_neigh_destroy(struct net_device *dev, - struct neighbour *n) -{ - struct net_device *lower_dev; - struct list_head *iter; - - netdev_for_each_lower_dev(dev, lower_dev, iter) { - if (!lower_dev->netdev_ops->ndo_neigh_destroy) - continue; - lower_dev->netdev_ops->ndo_neigh_destroy(lower_dev, n); - } -} -EXPORT_SYMBOL_GPL(netdev_default_l2upper_neigh_destroy); - static void dev_change_rx_flags(struct net_device *dev, int flags) { const struct net_device_ops *ops = dev->netdev_ops; @@ -6447,8 +6375,8 @@ int __dev_change_flags(struct net_device *dev, unsigned int flags) } /* NOTE: order of synchronization of IFF_PROMISC and IFF_ALLMULTI - is important. Some (broken) drivers set IFF_PROMISC, when - IFF_ALLMULTI is requested not asking us and not reporting. + * is important. Some (broken) drivers set IFF_PROMISC, when + * IFF_ALLMULTI is requested not asking us and not reporting. */ if ((flags ^ dev->gflags) & IFF_ALLMULTI) { int inc = (flags & IFF_ALLMULTI) ? 1 : -1; @@ -6746,6 +6674,7 @@ EXPORT_SYMBOL(dev_change_xdp_fd); static int dev_new_index(struct net *net) { int ifindex = net->ifindex; + for (;;) { if (++ifindex <= 0) ifindex = 1; @@ -6812,8 +6741,8 @@ static void rollback_registered_many(struct list_head *head) /* Notify protocols, that we are about to destroy - this device. They should clean all the things. - */ + * this device. They should clean all the things. + */ call_netdevice_notifiers(NETDEV_UNREGISTER, dev); if (!dev->rtnl_link_ops || @@ -6971,13 +6900,6 @@ static netdev_features_t netdev_fix_features(struct net_device *dev, features &= ~dev->gso_partial_features; } -#ifdef CONFIG_NET_RX_BUSY_POLL - if (dev->netdev_ops->ndo_busy_poll) - features |= NETIF_F_BUSY_POLL; - else -#endif - features &= ~NETIF_F_BUSY_POLL; - return features; } @@ -7166,6 +7088,7 @@ void netif_tx_stop_all_queues(struct net_device *dev) for (i = 0; i < dev->num_tx_queues; i++) { struct netdev_queue *txq = netdev_get_tx_queue(dev, i); + netif_tx_stop_queue(txq); } } @@ -7640,17 +7563,17 @@ void netdev_freemem(struct net_device *dev) } /** - * alloc_netdev_mqs - allocate network device - * @sizeof_priv: size of private data to allocate space for - * @name: device name format string - * @name_assign_type: origin of device name - * @setup: callback to initialize device - * @txqs: the number of TX subqueues to allocate - * @rxqs: the number of RX subqueues to allocate - * - * Allocates a struct net_device with private data area for driver use - * and performs basic initialization. Also allocates subqueue structs - * for each queue on the device. + * alloc_netdev_mqs - allocate network device + * @sizeof_priv: size of private data to allocate space for + * @name: device name format string + * @name_assign_type: origin of device name + * @setup: callback to initialize device + * @txqs: the number of TX subqueues to allocate + * @rxqs: the number of RX subqueues to allocate + * + * Allocates a struct net_device with private data area for driver use + * and performs basic initialization. Also allocates subqueue structs + * for each queue on the device. */ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, unsigned char name_assign_type, @@ -7762,13 +7685,13 @@ free_dev: EXPORT_SYMBOL(alloc_netdev_mqs); /** - * free_netdev - free network device - * @dev: device + * free_netdev - free network device + * @dev: device * - * This function does the last stage of destroying an allocated device - * interface. The reference to the device object is released. - * If this is the last reference then it will be freed. - * Must be called in process context. + * This function does the last stage of destroying an allocated device + * interface. The reference to the device object is released. If this + * is the last reference then it will be freed.Must be called in process + * context. */ void free_netdev(struct net_device *dev) { @@ -7950,12 +7873,12 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char dev_shutdown(dev); /* Notify protocols, that we are about to destroy - this device. They should clean all the things. - - Note that dev->reg_state stays at NETREG_REGISTERED. - This is wanted because this way 8021q and macvlan know - the device is just moving and can keep their slaves up. - */ + * this device. They should clean all the things. + * + * Note that dev->reg_state stays at NETREG_REGISTERED. + * This is wanted because this way 8021q and macvlan know + * the device is just moving and can keep their slaves up. + */ call_netdevice_notifiers(NETDEV_UNREGISTER, dev); rcu_barrier(); call_netdevice_notifiers(NETDEV_UNREGISTER_FINAL, dev); diff --git a/net/core/devlink.c b/net/core/devlink.c index 2b5bf9efa720..e9c1e6acfb6d 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -1392,9 +1392,9 @@ static int devlink_nl_cmd_sb_occ_max_clear_doit(struct sk_buff *skb, return -EOPNOTSUPP; } -static int devlink_eswitch_fill(struct sk_buff *msg, struct devlink *devlink, - enum devlink_command cmd, u32 portid, - u32 seq, int flags) +static int devlink_nl_eswitch_fill(struct sk_buff *msg, struct devlink *devlink, + enum devlink_command cmd, u32 portid, + u32 seq, int flags) { const struct devlink_ops *ops = devlink->ops; void *hdr; @@ -1408,50 +1408,52 @@ static int devlink_eswitch_fill(struct sk_buff *msg, struct devlink *devlink, err = devlink_nl_put_handle(msg, devlink); if (err) - goto out; + goto nla_put_failure; - err = ops->eswitch_mode_get(devlink, &mode); - if (err) - goto out; - err = nla_put_u16(msg, DEVLINK_ATTR_ESWITCH_MODE, mode); - if (err) - goto out; + if (ops->eswitch_mode_get) { + err = ops->eswitch_mode_get(devlink, &mode); + if (err) + goto nla_put_failure; + err = nla_put_u16(msg, DEVLINK_ATTR_ESWITCH_MODE, mode); + if (err) + goto nla_put_failure; + } if (ops->eswitch_inline_mode_get) { err = ops->eswitch_inline_mode_get(devlink, &inline_mode); if (err) - goto out; + goto nla_put_failure; err = nla_put_u8(msg, DEVLINK_ATTR_ESWITCH_INLINE_MODE, inline_mode); if (err) - goto out; + goto nla_put_failure; } genlmsg_end(msg, hdr); return 0; -out: +nla_put_failure: genlmsg_cancel(msg, hdr); return err; } -static int devlink_nl_cmd_eswitch_mode_get_doit(struct sk_buff *skb, - struct genl_info *info) +static int devlink_nl_cmd_eswitch_get_doit(struct sk_buff *skb, + struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; const struct devlink_ops *ops = devlink->ops; struct sk_buff *msg; int err; - if (!ops || !ops->eswitch_mode_get) + if (!ops) return -EOPNOTSUPP; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; - err = devlink_eswitch_fill(msg, devlink, DEVLINK_CMD_ESWITCH_MODE_GET, - info->snd_portid, info->snd_seq, 0); + err = devlink_nl_eswitch_fill(msg, devlink, DEVLINK_CMD_ESWITCH_GET, + info->snd_portid, info->snd_seq, 0); if (err) { nlmsg_free(msg); @@ -1461,8 +1463,8 @@ static int devlink_nl_cmd_eswitch_mode_get_doit(struct sk_buff *skb, return genlmsg_reply(msg, info); } -static int devlink_nl_cmd_eswitch_mode_set_doit(struct sk_buff *skb, - struct genl_info *info) +static int devlink_nl_cmd_eswitch_set_doit(struct sk_buff *skb, + struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; const struct devlink_ops *ops = devlink->ops; @@ -1629,15 +1631,15 @@ static const struct genl_ops devlink_nl_ops[] = { DEVLINK_NL_FLAG_LOCK_PORTS, }, { - .cmd = DEVLINK_CMD_ESWITCH_MODE_GET, - .doit = devlink_nl_cmd_eswitch_mode_get_doit, + .cmd = DEVLINK_CMD_ESWITCH_GET, + .doit = devlink_nl_cmd_eswitch_get_doit, .policy = devlink_nl_policy, .flags = GENL_ADMIN_PERM, .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, }, { - .cmd = DEVLINK_CMD_ESWITCH_MODE_SET, - .doit = devlink_nl_cmd_eswitch_mode_set_doit, + .cmd = DEVLINK_CMD_ESWITCH_SET, + .doit = devlink_nl_cmd_eswitch_set_doit, .policy = devlink_nl_policy, .flags = GENL_ADMIN_PERM, .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, diff --git a/net/core/dst.c b/net/core/dst.c index b5cbbe07f786..960e503b5a52 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -190,7 +190,6 @@ void dst_init(struct dst_entry *dst, struct dst_ops *ops, dst->__use = 0; dst->lastuse = jiffies; dst->flags = flags; - dst->pending_confirm = 0; dst->next = NULL; if (!(flags & DST_NOCOUNT)) dst_entries_add(ops, 1); diff --git a/net/core/ethtool.c b/net/core/ethtool.c index d92de0a1f0a4..be7bab1adcde 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -102,7 +102,6 @@ static const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN] [NETIF_F_RXFCS_BIT] = "rx-fcs", [NETIF_F_RXALL_BIT] = "rx-all", [NETIF_F_HW_L2FW_DOFFLOAD_BIT] = "l2-fwd-offload", - [NETIF_F_BUSY_POLL_BIT] = "busy-poll", [NETIF_F_HW_TC_BIT] = "hw-tc-offload", }; @@ -1820,11 +1819,13 @@ static int ethtool_get_strings(struct net_device *dev, void __user *useraddr) ret = __ethtool_get_sset_count(dev, gstrings.string_set); if (ret < 0) return ret; + if (ret > S32_MAX / ETH_GSTRING_LEN) + return -ENOMEM; + WARN_ON_ONCE(!ret); gstrings.len = ret; - - data = kcalloc(gstrings.len, ETH_GSTRING_LEN, GFP_USER); - if (!data) + data = vzalloc(gstrings.len * ETH_GSTRING_LEN); + if (gstrings.len && !data) return -ENOMEM; __ethtool_get_strings(dev, gstrings.string_set, data); @@ -1833,12 +1834,13 @@ static int ethtool_get_strings(struct net_device *dev, void __user *useraddr) if (copy_to_user(useraddr, &gstrings, sizeof(gstrings))) goto out; useraddr += sizeof(gstrings); - if (copy_to_user(useraddr, data, gstrings.len * ETH_GSTRING_LEN)) + if (gstrings.len && + copy_to_user(useraddr, data, gstrings.len * ETH_GSTRING_LEN)) goto out; ret = 0; out: - kfree(data); + vfree(data); return ret; } @@ -1915,14 +1917,15 @@ static int ethtool_get_stats(struct net_device *dev, void __user *useraddr) n_stats = ops->get_sset_count(dev, ETH_SS_STATS); if (n_stats < 0) return n_stats; - WARN_ON(n_stats == 0); - + if (n_stats > S32_MAX / sizeof(u64)) + return -ENOMEM; + WARN_ON_ONCE(!n_stats); if (copy_from_user(&stats, useraddr, sizeof(stats))) return -EFAULT; stats.n_stats = n_stats; - data = kmalloc(n_stats * sizeof(u64), GFP_USER); - if (!data) + data = vzalloc(n_stats * sizeof(u64)); + if (n_stats && !data) return -ENOMEM; ops->get_ethtool_stats(dev, &stats, data); @@ -1931,12 +1934,12 @@ static int ethtool_get_stats(struct net_device *dev, void __user *useraddr) if (copy_to_user(useraddr, &stats, sizeof(stats))) goto out; useraddr += sizeof(stats); - if (copy_to_user(useraddr, data, stats.n_stats * sizeof(u64))) + if (n_stats && copy_to_user(useraddr, data, n_stats * sizeof(u64))) goto out; ret = 0; out: - kfree(data); + vfree(data); return ret; } @@ -1951,17 +1954,18 @@ static int ethtool_get_phy_stats(struct net_device *dev, void __user *useraddr) return -EOPNOTSUPP; n_stats = phy_get_sset_count(phydev); - if (n_stats < 0) return n_stats; - WARN_ON(n_stats == 0); + if (n_stats > S32_MAX / sizeof(u64)) + return -ENOMEM; + WARN_ON_ONCE(!n_stats); if (copy_from_user(&stats, useraddr, sizeof(stats))) return -EFAULT; stats.n_stats = n_stats; - data = kmalloc_array(n_stats, sizeof(u64), GFP_USER); - if (!data) + data = vzalloc(n_stats * sizeof(u64)); + if (n_stats && !data) return -ENOMEM; mutex_lock(&phydev->lock); @@ -1972,12 +1976,12 @@ static int ethtool_get_phy_stats(struct net_device *dev, void __user *useraddr) if (copy_to_user(useraddr, &stats, sizeof(stats))) goto out; useraddr += sizeof(stats); - if (copy_to_user(useraddr, data, stats.n_stats * sizeof(u64))) + if (n_stats && copy_to_user(useraddr, data, n_stats * sizeof(u64))) goto out; ret = 0; out: - kfree(data); + vfree(data); return ret; } diff --git a/net/core/filter.c b/net/core/filter.c index 1969b3f118c1..e466e0040137 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -76,9 +76,10 @@ int sk_filter_trim_cap(struct sock *sk, struct sk_buff *skb, unsigned int cap) * allow SOCK_MEMALLOC sockets to use it as this socket is * helping free memory */ - if (skb_pfmemalloc(skb) && !sock_flag(sk, SOCK_MEMALLOC)) + if (skb_pfmemalloc(skb) && !sock_flag(sk, SOCK_MEMALLOC)) { + NET_INC_STATS(sock_net(sk), LINUX_MIB_PFMEMALLOCDROP); return -ENOMEM; - + } err = BPF_CGROUP_RUN_PROG_INET_INGRESS(sk, skb); if (err) return err; @@ -1416,8 +1417,8 @@ static const struct bpf_func_proto bpf_skb_store_bytes_proto = { .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, - .arg3_type = ARG_PTR_TO_STACK, - .arg4_type = ARG_CONST_STACK_SIZE, + .arg3_type = ARG_PTR_TO_MEM, + .arg4_type = ARG_CONST_SIZE, .arg5_type = ARG_ANYTHING, }; @@ -1447,8 +1448,8 @@ static const struct bpf_func_proto bpf_skb_load_bytes_proto = { .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, - .arg3_type = ARG_PTR_TO_RAW_STACK, - .arg4_type = ARG_CONST_STACK_SIZE, + .arg3_type = ARG_PTR_TO_UNINIT_MEM, + .arg4_type = ARG_CONST_SIZE, }; BPF_CALL_2(bpf_skb_pull_data, struct sk_buff *, skb, u32, len) @@ -1522,10 +1523,11 @@ BPF_CALL_5(bpf_l4_csum_replace, struct sk_buff *, skb, u32, offset, { bool is_pseudo = flags & BPF_F_PSEUDO_HDR; bool is_mmzero = flags & BPF_F_MARK_MANGLED_0; + bool do_mforce = flags & BPF_F_MARK_ENFORCE; __sum16 *ptr; - if (unlikely(flags & ~(BPF_F_MARK_MANGLED_0 | BPF_F_PSEUDO_HDR | - BPF_F_HDR_FIELD_MASK))) + if (unlikely(flags & ~(BPF_F_MARK_MANGLED_0 | BPF_F_MARK_ENFORCE | + BPF_F_PSEUDO_HDR | BPF_F_HDR_FIELD_MASK))) return -EINVAL; if (unlikely(offset > 0xffff || offset & 1)) return -EFAULT; @@ -1533,7 +1535,7 @@ BPF_CALL_5(bpf_l4_csum_replace, struct sk_buff *, skb, u32, offset, return -EFAULT; ptr = (__sum16 *)(skb->data + offset); - if (is_mmzero && !*ptr) + if (is_mmzero && !do_mforce && !*ptr) return 0; switch (flags & BPF_F_HDR_FIELD_MASK) { @@ -1601,10 +1603,10 @@ static const struct bpf_func_proto bpf_csum_diff_proto = { .gpl_only = false, .pkt_access = true, .ret_type = RET_INTEGER, - .arg1_type = ARG_PTR_TO_STACK, - .arg2_type = ARG_CONST_STACK_SIZE_OR_ZERO, - .arg3_type = ARG_PTR_TO_STACK, - .arg4_type = ARG_CONST_STACK_SIZE_OR_ZERO, + .arg1_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_CONST_SIZE_OR_ZERO, + .arg3_type = ARG_PTR_TO_MEM, + .arg4_type = ARG_CONST_SIZE_OR_ZERO, .arg5_type = ARG_ANYTHING, }; @@ -2306,8 +2308,8 @@ static const struct bpf_func_proto bpf_skb_event_output_proto = { .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, - .arg4_type = ARG_PTR_TO_STACK, - .arg5_type = ARG_CONST_STACK_SIZE, + .arg4_type = ARG_PTR_TO_MEM, + .arg5_type = ARG_CONST_SIZE, }; static unsigned short bpf_tunnel_key_af(u64 flags) @@ -2377,8 +2379,8 @@ static const struct bpf_func_proto bpf_skb_get_tunnel_key_proto = { .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, - .arg2_type = ARG_PTR_TO_RAW_STACK, - .arg3_type = ARG_CONST_STACK_SIZE, + .arg2_type = ARG_PTR_TO_UNINIT_MEM, + .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_ANYTHING, }; @@ -2412,8 +2414,8 @@ static const struct bpf_func_proto bpf_skb_get_tunnel_opt_proto = { .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, - .arg2_type = ARG_PTR_TO_RAW_STACK, - .arg3_type = ARG_CONST_STACK_SIZE, + .arg2_type = ARG_PTR_TO_UNINIT_MEM, + .arg3_type = ARG_CONST_SIZE, }; static struct metadata_dst __percpu *md_dst; @@ -2483,8 +2485,8 @@ static const struct bpf_func_proto bpf_skb_set_tunnel_key_proto = { .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, - .arg2_type = ARG_PTR_TO_STACK, - .arg3_type = ARG_CONST_STACK_SIZE, + .arg2_type = ARG_PTR_TO_MEM, + .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_ANYTHING, }; @@ -2509,8 +2511,8 @@ static const struct bpf_func_proto bpf_skb_set_tunnel_opt_proto = { .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, - .arg2_type = ARG_PTR_TO_STACK, - .arg3_type = ARG_CONST_STACK_SIZE, + .arg2_type = ARG_PTR_TO_MEM, + .arg3_type = ARG_CONST_SIZE, }; static const struct bpf_func_proto * @@ -2593,12 +2595,12 @@ static const struct bpf_func_proto bpf_xdp_event_output_proto = { .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, - .arg4_type = ARG_PTR_TO_STACK, - .arg5_type = ARG_CONST_STACK_SIZE, + .arg4_type = ARG_PTR_TO_MEM, + .arg5_type = ARG_CONST_SIZE, }; static const struct bpf_func_proto * -sk_filter_func_proto(enum bpf_func_id func_id) +bpf_base_func_proto(enum bpf_func_id func_id) { switch (func_id) { case BPF_FUNC_map_lookup_elem: @@ -2626,6 +2628,17 @@ sk_filter_func_proto(enum bpf_func_id func_id) } static const struct bpf_func_proto * +sk_filter_func_proto(enum bpf_func_id func_id) +{ + switch (func_id) { + case BPF_FUNC_skb_load_bytes: + return &bpf_skb_load_bytes_proto; + default: + return bpf_base_func_proto(func_id); + } +} + +static const struct bpf_func_proto * tc_cls_act_func_proto(enum bpf_func_id func_id) { switch (func_id) { @@ -2680,7 +2693,7 @@ tc_cls_act_func_proto(enum bpf_func_id func_id) case BPF_FUNC_skb_under_cgroup: return &bpf_skb_under_cgroup_proto; default: - return sk_filter_func_proto(func_id); + return bpf_base_func_proto(func_id); } } @@ -2695,7 +2708,7 @@ xdp_func_proto(enum bpf_func_id func_id) case BPF_FUNC_xdp_adjust_head: return &bpf_xdp_adjust_head_proto; default: - return sk_filter_func_proto(func_id); + return bpf_base_func_proto(func_id); } } @@ -2706,7 +2719,7 @@ cg_skb_func_proto(enum bpf_func_id func_id) case BPF_FUNC_skb_load_bytes: return &bpf_skb_load_bytes_proto; default: - return sk_filter_func_proto(func_id); + return bpf_base_func_proto(func_id); } } @@ -2733,7 +2746,7 @@ lwt_inout_func_proto(enum bpf_func_id func_id) case BPF_FUNC_skb_under_cgroup: return &bpf_skb_under_cgroup_proto; default: - return sk_filter_func_proto(func_id); + return bpf_base_func_proto(func_id); } } @@ -2776,11 +2789,22 @@ static bool __is_valid_access(int off, int size) { if (off < 0 || off >= sizeof(struct __sk_buff)) return false; + /* The verifier guarantees that size > 0. */ if (off % size != 0) return false; - if (size != sizeof(__u32)) - return false; + + switch (off) { + case offsetof(struct __sk_buff, cb[0]) ... + offsetof(struct __sk_buff, cb[4]) + sizeof(__u32) - 1: + if (off + size > + offsetof(struct __sk_buff, cb[4]) + sizeof(__u32)) + return false; + break; + default: + if (size != sizeof(__u32)) + return false; + } return true; } @@ -2799,7 +2823,7 @@ static bool sk_filter_is_valid_access(int off, int size, if (type == BPF_WRITE) { switch (off) { case offsetof(struct __sk_buff, cb[0]) ... - offsetof(struct __sk_buff, cb[4]): + offsetof(struct __sk_buff, cb[4]) + sizeof(__u32) - 1: break; default: return false; @@ -2823,7 +2847,7 @@ static bool lwt_is_valid_access(int off, int size, case offsetof(struct __sk_buff, mark): case offsetof(struct __sk_buff, priority): case offsetof(struct __sk_buff, cb[0]) ... - offsetof(struct __sk_buff, cb[4]): + offsetof(struct __sk_buff, cb[4]) + sizeof(__u32) - 1: break; default: return false; @@ -2915,7 +2939,7 @@ static bool tc_cls_act_is_valid_access(int off, int size, case offsetof(struct __sk_buff, tc_index): case offsetof(struct __sk_buff, priority): case offsetof(struct __sk_buff, cb[0]) ... - offsetof(struct __sk_buff, cb[4]): + offsetof(struct __sk_buff, cb[4]) + sizeof(__u32) - 1: case offsetof(struct __sk_buff, tc_classid): break; default: @@ -2972,32 +2996,33 @@ void bpf_warn_invalid_xdp_action(u32 act) } EXPORT_SYMBOL_GPL(bpf_warn_invalid_xdp_action); -static u32 sk_filter_convert_ctx_access(enum bpf_access_type type, int dst_reg, - int src_reg, int ctx_off, - struct bpf_insn *insn_buf, - struct bpf_prog *prog) +static u32 bpf_convert_ctx_access(enum bpf_access_type type, + const struct bpf_insn *si, + struct bpf_insn *insn_buf, + struct bpf_prog *prog) { struct bpf_insn *insn = insn_buf; + int off; - switch (ctx_off) { + switch (si->off) { case offsetof(struct __sk_buff, len): BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, len) != 4); - *insn++ = BPF_LDX_MEM(BPF_W, dst_reg, src_reg, + *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, offsetof(struct sk_buff, len)); break; case offsetof(struct __sk_buff, protocol): BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, protocol) != 2); - *insn++ = BPF_LDX_MEM(BPF_H, dst_reg, src_reg, + *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->src_reg, offsetof(struct sk_buff, protocol)); break; case offsetof(struct __sk_buff, vlan_proto): BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, vlan_proto) != 2); - *insn++ = BPF_LDX_MEM(BPF_H, dst_reg, src_reg, + *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->src_reg, offsetof(struct sk_buff, vlan_proto)); break; @@ -3005,17 +3030,17 @@ static u32 sk_filter_convert_ctx_access(enum bpf_access_type type, int dst_reg, BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, priority) != 4); if (type == BPF_WRITE) - *insn++ = BPF_STX_MEM(BPF_W, dst_reg, src_reg, + *insn++ = BPF_STX_MEM(BPF_W, si->dst_reg, si->src_reg, offsetof(struct sk_buff, priority)); else - *insn++ = BPF_LDX_MEM(BPF_W, dst_reg, src_reg, + *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, offsetof(struct sk_buff, priority)); break; case offsetof(struct __sk_buff, ingress_ifindex): BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, skb_iif) != 4); - *insn++ = BPF_LDX_MEM(BPF_W, dst_reg, src_reg, + *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, offsetof(struct sk_buff, skb_iif)); break; @@ -3023,17 +3048,17 @@ static u32 sk_filter_convert_ctx_access(enum bpf_access_type type, int dst_reg, BUILD_BUG_ON(FIELD_SIZEOF(struct net_device, ifindex) != 4); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, dev), - dst_reg, src_reg, + si->dst_reg, si->src_reg, offsetof(struct sk_buff, dev)); - *insn++ = BPF_JMP_IMM(BPF_JEQ, dst_reg, 0, 1); - *insn++ = BPF_LDX_MEM(BPF_W, dst_reg, dst_reg, + *insn++ = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, 1); + *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, offsetof(struct net_device, ifindex)); break; case offsetof(struct __sk_buff, hash): BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, hash) != 4); - *insn++ = BPF_LDX_MEM(BPF_W, dst_reg, src_reg, + *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, offsetof(struct sk_buff, hash)); break; @@ -3041,63 +3066,77 @@ static u32 sk_filter_convert_ctx_access(enum bpf_access_type type, int dst_reg, BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, mark) != 4); if (type == BPF_WRITE) - *insn++ = BPF_STX_MEM(BPF_W, dst_reg, src_reg, + *insn++ = BPF_STX_MEM(BPF_W, si->dst_reg, si->src_reg, offsetof(struct sk_buff, mark)); else - *insn++ = BPF_LDX_MEM(BPF_W, dst_reg, src_reg, + *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, offsetof(struct sk_buff, mark)); break; case offsetof(struct __sk_buff, pkt_type): - return convert_skb_access(SKF_AD_PKTTYPE, dst_reg, src_reg, insn); + return convert_skb_access(SKF_AD_PKTTYPE, si->dst_reg, + si->src_reg, insn); case offsetof(struct __sk_buff, queue_mapping): - return convert_skb_access(SKF_AD_QUEUE, dst_reg, src_reg, insn); + return convert_skb_access(SKF_AD_QUEUE, si->dst_reg, + si->src_reg, insn); case offsetof(struct __sk_buff, vlan_present): return convert_skb_access(SKF_AD_VLAN_TAG_PRESENT, - dst_reg, src_reg, insn); + si->dst_reg, si->src_reg, insn); case offsetof(struct __sk_buff, vlan_tci): return convert_skb_access(SKF_AD_VLAN_TAG, - dst_reg, src_reg, insn); + si->dst_reg, si->src_reg, insn); case offsetof(struct __sk_buff, cb[0]) ... - offsetof(struct __sk_buff, cb[4]): + offsetof(struct __sk_buff, cb[4]) + sizeof(__u32) - 1: BUILD_BUG_ON(FIELD_SIZEOF(struct qdisc_skb_cb, data) < 20); + BUILD_BUG_ON((offsetof(struct sk_buff, cb) + + offsetof(struct qdisc_skb_cb, data)) % + sizeof(__u64)); prog->cb_access = 1; - ctx_off -= offsetof(struct __sk_buff, cb[0]); - ctx_off += offsetof(struct sk_buff, cb); - ctx_off += offsetof(struct qdisc_skb_cb, data); + off = si->off; + off -= offsetof(struct __sk_buff, cb[0]); + off += offsetof(struct sk_buff, cb); + off += offsetof(struct qdisc_skb_cb, data); if (type == BPF_WRITE) - *insn++ = BPF_STX_MEM(BPF_W, dst_reg, src_reg, ctx_off); + *insn++ = BPF_STX_MEM(BPF_SIZE(si->code), si->dst_reg, + si->src_reg, off); else - *insn++ = BPF_LDX_MEM(BPF_W, dst_reg, src_reg, ctx_off); + *insn++ = BPF_LDX_MEM(BPF_SIZE(si->code), si->dst_reg, + si->src_reg, off); break; case offsetof(struct __sk_buff, tc_classid): - ctx_off -= offsetof(struct __sk_buff, tc_classid); - ctx_off += offsetof(struct sk_buff, cb); - ctx_off += offsetof(struct qdisc_skb_cb, tc_classid); + BUILD_BUG_ON(FIELD_SIZEOF(struct qdisc_skb_cb, tc_classid) != 2); + + off = si->off; + off -= offsetof(struct __sk_buff, tc_classid); + off += offsetof(struct sk_buff, cb); + off += offsetof(struct qdisc_skb_cb, tc_classid); if (type == BPF_WRITE) - *insn++ = BPF_STX_MEM(BPF_H, dst_reg, src_reg, ctx_off); + *insn++ = BPF_STX_MEM(BPF_H, si->dst_reg, + si->src_reg, off); else - *insn++ = BPF_LDX_MEM(BPF_H, dst_reg, src_reg, ctx_off); + *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, + si->src_reg, off); break; case offsetof(struct __sk_buff, data): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, data), - dst_reg, src_reg, + si->dst_reg, si->src_reg, offsetof(struct sk_buff, data)); break; case offsetof(struct __sk_buff, data_end): - ctx_off -= offsetof(struct __sk_buff, data_end); - ctx_off += offsetof(struct sk_buff, cb); - ctx_off += offsetof(struct bpf_skb_data_end, data_end); - *insn++ = BPF_LDX_MEM(BPF_SIZEOF(void *), dst_reg, src_reg, - ctx_off); + off = si->off; + off -= offsetof(struct __sk_buff, data_end); + off += offsetof(struct sk_buff, cb); + off += offsetof(struct bpf_skb_data_end, data_end); + *insn++ = BPF_LDX_MEM(BPF_SIZEOF(void *), si->dst_reg, + si->src_reg, off); break; case offsetof(struct __sk_buff, tc_index): @@ -3105,110 +3144,107 @@ static u32 sk_filter_convert_ctx_access(enum bpf_access_type type, int dst_reg, BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, tc_index) != 2); if (type == BPF_WRITE) - *insn++ = BPF_STX_MEM(BPF_H, dst_reg, src_reg, + *insn++ = BPF_STX_MEM(BPF_H, si->dst_reg, si->src_reg, offsetof(struct sk_buff, tc_index)); else - *insn++ = BPF_LDX_MEM(BPF_H, dst_reg, src_reg, + *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->src_reg, offsetof(struct sk_buff, tc_index)); - break; #else if (type == BPF_WRITE) - *insn++ = BPF_MOV64_REG(dst_reg, dst_reg); + *insn++ = BPF_MOV64_REG(si->dst_reg, si->dst_reg); else - *insn++ = BPF_MOV64_IMM(dst_reg, 0); - break; + *insn++ = BPF_MOV64_IMM(si->dst_reg, 0); #endif + break; } return insn - insn_buf; } static u32 sock_filter_convert_ctx_access(enum bpf_access_type type, - int dst_reg, int src_reg, - int ctx_off, + const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog) { struct bpf_insn *insn = insn_buf; - switch (ctx_off) { + switch (si->off) { case offsetof(struct bpf_sock, bound_dev_if): BUILD_BUG_ON(FIELD_SIZEOF(struct sock, sk_bound_dev_if) != 4); if (type == BPF_WRITE) - *insn++ = BPF_STX_MEM(BPF_W, dst_reg, src_reg, + *insn++ = BPF_STX_MEM(BPF_W, si->dst_reg, si->src_reg, offsetof(struct sock, sk_bound_dev_if)); else - *insn++ = BPF_LDX_MEM(BPF_W, dst_reg, src_reg, + *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, offsetof(struct sock, sk_bound_dev_if)); break; case offsetof(struct bpf_sock, family): BUILD_BUG_ON(FIELD_SIZEOF(struct sock, sk_family) != 2); - *insn++ = BPF_LDX_MEM(BPF_H, dst_reg, src_reg, + *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->src_reg, offsetof(struct sock, sk_family)); break; case offsetof(struct bpf_sock, type): - *insn++ = BPF_LDX_MEM(BPF_W, dst_reg, src_reg, + *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, offsetof(struct sock, __sk_flags_offset)); - *insn++ = BPF_ALU32_IMM(BPF_AND, dst_reg, SK_FL_TYPE_MASK); - *insn++ = BPF_ALU32_IMM(BPF_RSH, dst_reg, SK_FL_TYPE_SHIFT); + *insn++ = BPF_ALU32_IMM(BPF_AND, si->dst_reg, SK_FL_TYPE_MASK); + *insn++ = BPF_ALU32_IMM(BPF_RSH, si->dst_reg, SK_FL_TYPE_SHIFT); break; case offsetof(struct bpf_sock, protocol): - *insn++ = BPF_LDX_MEM(BPF_W, dst_reg, src_reg, + *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, offsetof(struct sock, __sk_flags_offset)); - *insn++ = BPF_ALU32_IMM(BPF_AND, dst_reg, SK_FL_PROTO_MASK); - *insn++ = BPF_ALU32_IMM(BPF_RSH, dst_reg, SK_FL_PROTO_SHIFT); + *insn++ = BPF_ALU32_IMM(BPF_AND, si->dst_reg, SK_FL_PROTO_MASK); + *insn++ = BPF_ALU32_IMM(BPF_RSH, si->dst_reg, SK_FL_PROTO_SHIFT); break; } return insn - insn_buf; } -static u32 tc_cls_act_convert_ctx_access(enum bpf_access_type type, int dst_reg, - int src_reg, int ctx_off, +static u32 tc_cls_act_convert_ctx_access(enum bpf_access_type type, + const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog) { struct bpf_insn *insn = insn_buf; - switch (ctx_off) { + switch (si->off) { case offsetof(struct __sk_buff, ifindex): BUILD_BUG_ON(FIELD_SIZEOF(struct net_device, ifindex) != 4); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, dev), - dst_reg, src_reg, + si->dst_reg, si->src_reg, offsetof(struct sk_buff, dev)); - *insn++ = BPF_LDX_MEM(BPF_W, dst_reg, dst_reg, + *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, offsetof(struct net_device, ifindex)); break; default: - return sk_filter_convert_ctx_access(type, dst_reg, src_reg, - ctx_off, insn_buf, prog); + return bpf_convert_ctx_access(type, si, insn_buf, prog); } return insn - insn_buf; } -static u32 xdp_convert_ctx_access(enum bpf_access_type type, int dst_reg, - int src_reg, int ctx_off, +static u32 xdp_convert_ctx_access(enum bpf_access_type type, + const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog) { struct bpf_insn *insn = insn_buf; - switch (ctx_off) { + switch (si->off) { case offsetof(struct xdp_md, data): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_buff, data), - dst_reg, src_reg, + si->dst_reg, si->src_reg, offsetof(struct xdp_buff, data)); break; case offsetof(struct xdp_md, data_end): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_buff, data_end), - dst_reg, src_reg, + si->dst_reg, si->src_reg, offsetof(struct xdp_buff, data_end)); break; } @@ -3219,7 +3255,7 @@ static u32 xdp_convert_ctx_access(enum bpf_access_type type, int dst_reg, static const struct bpf_verifier_ops sk_filter_ops = { .get_func_proto = sk_filter_func_proto, .is_valid_access = sk_filter_is_valid_access, - .convert_ctx_access = sk_filter_convert_ctx_access, + .convert_ctx_access = bpf_convert_ctx_access, }; static const struct bpf_verifier_ops tc_cls_act_ops = { @@ -3238,69 +3274,69 @@ static const struct bpf_verifier_ops xdp_ops = { static const struct bpf_verifier_ops cg_skb_ops = { .get_func_proto = cg_skb_func_proto, .is_valid_access = sk_filter_is_valid_access, - .convert_ctx_access = sk_filter_convert_ctx_access, + .convert_ctx_access = bpf_convert_ctx_access, }; static const struct bpf_verifier_ops lwt_inout_ops = { .get_func_proto = lwt_inout_func_proto, .is_valid_access = lwt_is_valid_access, - .convert_ctx_access = sk_filter_convert_ctx_access, + .convert_ctx_access = bpf_convert_ctx_access, }; static const struct bpf_verifier_ops lwt_xmit_ops = { .get_func_proto = lwt_xmit_func_proto, .is_valid_access = lwt_is_valid_access, - .convert_ctx_access = sk_filter_convert_ctx_access, + .convert_ctx_access = bpf_convert_ctx_access, .gen_prologue = tc_cls_act_prologue, }; static const struct bpf_verifier_ops cg_sock_ops = { - .get_func_proto = sk_filter_func_proto, + .get_func_proto = bpf_base_func_proto, .is_valid_access = sock_filter_is_valid_access, .convert_ctx_access = sock_filter_convert_ctx_access, }; -static struct bpf_prog_type_list sk_filter_type __read_mostly = { +static struct bpf_prog_type_list sk_filter_type __ro_after_init = { .ops = &sk_filter_ops, .type = BPF_PROG_TYPE_SOCKET_FILTER, }; -static struct bpf_prog_type_list sched_cls_type __read_mostly = { +static struct bpf_prog_type_list sched_cls_type __ro_after_init = { .ops = &tc_cls_act_ops, .type = BPF_PROG_TYPE_SCHED_CLS, }; -static struct bpf_prog_type_list sched_act_type __read_mostly = { +static struct bpf_prog_type_list sched_act_type __ro_after_init = { .ops = &tc_cls_act_ops, .type = BPF_PROG_TYPE_SCHED_ACT, }; -static struct bpf_prog_type_list xdp_type __read_mostly = { +static struct bpf_prog_type_list xdp_type __ro_after_init = { .ops = &xdp_ops, .type = BPF_PROG_TYPE_XDP, }; -static struct bpf_prog_type_list cg_skb_type __read_mostly = { +static struct bpf_prog_type_list cg_skb_type __ro_after_init = { .ops = &cg_skb_ops, .type = BPF_PROG_TYPE_CGROUP_SKB, }; -static struct bpf_prog_type_list lwt_in_type __read_mostly = { +static struct bpf_prog_type_list lwt_in_type __ro_after_init = { .ops = &lwt_inout_ops, .type = BPF_PROG_TYPE_LWT_IN, }; -static struct bpf_prog_type_list lwt_out_type __read_mostly = { +static struct bpf_prog_type_list lwt_out_type __ro_after_init = { .ops = &lwt_inout_ops, .type = BPF_PROG_TYPE_LWT_OUT, }; -static struct bpf_prog_type_list lwt_xmit_type __read_mostly = { +static struct bpf_prog_type_list lwt_xmit_type __ro_after_init = { .ops = &lwt_xmit_ops, .type = BPF_PROG_TYPE_LWT_XMIT, }; -static struct bpf_prog_type_list cg_sock_type __read_mostly = { +static struct bpf_prog_type_list cg_sock_type __ro_after_init = { .ops = &cg_sock_ops, .type = BPF_PROG_TYPE_CGROUP_SOCK }; diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 1b7673aac59d..c35aae13c8d2 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -138,6 +138,7 @@ bool __skb_flow_dissect(const struct sk_buff *skb, struct flow_dissector_key_control *key_control; struct flow_dissector_key_basic *key_basic; struct flow_dissector_key_addrs *key_addrs; + struct flow_dissector_key_arp *key_arp; struct flow_dissector_key_ports *key_ports; struct flow_dissector_key_icmp *key_icmp; struct flow_dissector_key_tags *key_tags; @@ -379,6 +380,62 @@ mpls: nhoff += FCOE_HEADER_LEN; goto out_good; + + case htons(ETH_P_ARP): + case htons(ETH_P_RARP): { + struct { + unsigned char ar_sha[ETH_ALEN]; + unsigned char ar_sip[4]; + unsigned char ar_tha[ETH_ALEN]; + unsigned char ar_tip[4]; + } *arp_eth, _arp_eth; + const struct arphdr *arp; + struct arphdr *_arp; + + arp = __skb_header_pointer(skb, nhoff, sizeof(_arp), data, + hlen, &_arp); + if (!arp) + goto out_bad; + + if (arp->ar_hrd != htons(ARPHRD_ETHER) || + arp->ar_pro != htons(ETH_P_IP) || + arp->ar_hln != ETH_ALEN || + arp->ar_pln != 4 || + (arp->ar_op != htons(ARPOP_REPLY) && + arp->ar_op != htons(ARPOP_REQUEST))) + goto out_bad; + + arp_eth = __skb_header_pointer(skb, nhoff + sizeof(_arp), + sizeof(_arp_eth), data, + hlen, + &_arp_eth); + if (!arp_eth) + goto out_bad; + + if (dissector_uses_key(flow_dissector, + FLOW_DISSECTOR_KEY_ARP)) { + + key_arp = skb_flow_dissector_target(flow_dissector, + FLOW_DISSECTOR_KEY_ARP, + target_container); + + memcpy(&key_arp->sip, arp_eth->ar_sip, + sizeof(key_arp->sip)); + memcpy(&key_arp->tip, arp_eth->ar_tip, + sizeof(key_arp->tip)); + + /* Only store the lower byte of the opcode; + * this covers ARPOP_REPLY and ARPOP_REQUEST. + */ + key_arp->op = ntohs(arp->ar_op) & 0xff; + + ether_addr_copy(key_arp->sha, arp_eth->ar_sha); + ether_addr_copy(key_arp->tha, arp_eth->ar_tha); + } + + goto out_good; + } + default: goto out_bad; } diff --git a/net/core/gro_cells.c b/net/core/gro_cells.c new file mode 100644 index 000000000000..c98bbfbd26b8 --- /dev/null +++ b/net/core/gro_cells.c @@ -0,0 +1,92 @@ +#include <linux/skbuff.h> +#include <linux/slab.h> +#include <linux/netdevice.h> +#include <net/gro_cells.h> + +struct gro_cell { + struct sk_buff_head napi_skbs; + struct napi_struct napi; +}; + +int gro_cells_receive(struct gro_cells *gcells, struct sk_buff *skb) +{ + struct net_device *dev = skb->dev; + struct gro_cell *cell; + + if (!gcells->cells || skb_cloned(skb) || !(dev->features & NETIF_F_GRO)) + return netif_rx(skb); + + cell = this_cpu_ptr(gcells->cells); + + if (skb_queue_len(&cell->napi_skbs) > netdev_max_backlog) { + atomic_long_inc(&dev->rx_dropped); + kfree_skb(skb); + return NET_RX_DROP; + } + + __skb_queue_tail(&cell->napi_skbs, skb); + if (skb_queue_len(&cell->napi_skbs) == 1) + napi_schedule(&cell->napi); + return NET_RX_SUCCESS; +} +EXPORT_SYMBOL(gro_cells_receive); + +/* called under BH context */ +static int gro_cell_poll(struct napi_struct *napi, int budget) +{ + struct gro_cell *cell = container_of(napi, struct gro_cell, napi); + struct sk_buff *skb; + int work_done = 0; + + while (work_done < budget) { + skb = __skb_dequeue(&cell->napi_skbs); + if (!skb) + break; + napi_gro_receive(napi, skb); + work_done++; + } + + if (work_done < budget) + napi_complete_done(napi, work_done); + return work_done; +} + +int gro_cells_init(struct gro_cells *gcells, struct net_device *dev) +{ + int i; + + gcells->cells = alloc_percpu(struct gro_cell); + if (!gcells->cells) + return -ENOMEM; + + for_each_possible_cpu(i) { + struct gro_cell *cell = per_cpu_ptr(gcells->cells, i); + + __skb_queue_head_init(&cell->napi_skbs); + + set_bit(NAPI_STATE_NO_BUSY_POLL, &cell->napi.state); + + netif_napi_add(dev, &cell->napi, gro_cell_poll, + NAPI_POLL_WEIGHT); + napi_enable(&cell->napi); + } + return 0; +} +EXPORT_SYMBOL(gro_cells_init); + +void gro_cells_destroy(struct gro_cells *gcells) +{ + int i; + + if (!gcells->cells) + return; + for_each_possible_cpu(i) { + struct gro_cell *cell = per_cpu_ptr(gcells->cells, i); + + netif_napi_del(&cell->napi); + __skb_queue_purge(&cell->napi_skbs); + } + free_percpu(gcells->cells); + gcells->cells = NULL; +} +EXPORT_SYMBOL(gro_cells_destroy); diff --git a/net/core/lwt_bpf.c b/net/core/lwt_bpf.c index b3eef90b2df9..0cfe7b0216c3 100644 --- a/net/core/lwt_bpf.c +++ b/net/core/lwt_bpf.c @@ -237,7 +237,7 @@ static const struct nla_policy bpf_nl_policy[LWT_BPF_MAX + 1] = { [LWT_BPF_XMIT_HEADROOM] = { .type = NLA_U32 }, }; -static int bpf_build_state(struct net_device *dev, struct nlattr *nla, +static int bpf_build_state(struct nlattr *nla, unsigned int family, const void *cfg, struct lwtunnel_state **ts) { @@ -352,7 +352,7 @@ static int bpf_encap_nlsize(struct lwtunnel_state *lwtstate) 0; } -int bpf_lwt_prog_cmp(struct bpf_lwt_prog *a, struct bpf_lwt_prog *b) +static int bpf_lwt_prog_cmp(struct bpf_lwt_prog *a, struct bpf_lwt_prog *b) { /* FIXME: * The LWT state is currently rebuilt for delete requests which diff --git a/net/core/lwtunnel.c b/net/core/lwtunnel.c index c23465005f2f..6df9f8fabf0c 100644 --- a/net/core/lwtunnel.c +++ b/net/core/lwtunnel.c @@ -101,7 +101,7 @@ int lwtunnel_encap_del_ops(const struct lwtunnel_encap_ops *ops, } EXPORT_SYMBOL(lwtunnel_encap_del_ops); -int lwtunnel_build_state(struct net_device *dev, u16 encap_type, +int lwtunnel_build_state(u16 encap_type, struct nlattr *encap, unsigned int family, const void *cfg, struct lwtunnel_state **lws) { @@ -116,7 +116,7 @@ int lwtunnel_build_state(struct net_device *dev, u16 encap_type, rcu_read_lock(); ops = rcu_dereference(lwtun_encaps[encap_type]); if (likely(ops && ops->build_state && try_module_get(ops->owner))) { - ret = ops->build_state(dev, encap, family, cfg, lws); + ret = ops->build_state(encap, family, cfg, lws); if (ret) module_put(ops->owner); } diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c index 2ec86fc552df..756637dc7a57 100644 --- a/net/core/netprio_cgroup.c +++ b/net/core/netprio_cgroup.c @@ -13,6 +13,7 @@ #include <linux/slab.h> #include <linux/types.h> +#include <linux/module.h> #include <linux/string.h> #include <linux/errno.h> #include <linux/skbuff.h> diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 8e69ce472236..96947f5d41e4 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -3439,9 +3439,7 @@ static void pktgen_xmit(struct pktgen_dev *pkt_dev) /* skb was 'freed' by stack, so clean few * bits and reuse it */ -#ifdef CONFIG_NET_CLS_ACT - skb->tc_verd = 0; /* reset reclass/redir ttl */ -#endif + skb_reset_tc(skb); } while (--burst > 0); goto out; /* Skips xmit_mode M_START_XMIT */ } else if (pkt_dev->xmit_mode == M_QUEUE_XMIT) { diff --git a/net/core/request_sock.c b/net/core/request_sock.c index 5d26056b6d8f..9b8727c67b58 100644 --- a/net/core/request_sock.c +++ b/net/core/request_sock.c @@ -34,8 +34,6 @@ * and it will increase in proportion to the memory of machine. * Note : Dont forget somaxconn that may limit backlog too. */ -int sysctl_max_syn_backlog = 256; -EXPORT_SYMBOL(sysctl_max_syn_backlog); void reqsk_queue_alloc(struct request_sock_queue *queue) { diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 75e3ea7bda08..c4e84c558240 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -837,8 +837,7 @@ static void copy_rtnl_link_stats(struct rtnl_link_stats *a, static inline int rtnl_vfinfo_size(const struct net_device *dev, u32 ext_filter_mask) { - if (dev->dev.parent && dev_is_pci(dev->dev.parent) && - (ext_filter_mask & RTEXT_FILTER_VF)) { + if (dev->dev.parent && (ext_filter_mask & RTEXT_FILTER_VF)) { int num_vfs = dev_num_vf(dev->dev.parent); size_t size = nla_total_size(0); size += num_vfs * @@ -877,8 +876,6 @@ static size_t rtnl_port_size(const struct net_device *dev, { size_t port_size = nla_total_size(4) /* PORT_VF */ + nla_total_size(PORT_PROFILE_MAX) /* PORT_PROFILE */ - + nla_total_size(sizeof(struct ifla_port_vsi)) - /* PORT_VSI_TYPE */ + nla_total_size(PORT_UUID_MAX) /* PORT_INSTANCE_UUID */ + nla_total_size(PORT_UUID_MAX) /* PORT_HOST_UUID */ + nla_total_size(1) /* PROT_VDP_REQUEST */ @@ -1492,14 +1489,19 @@ static const struct nla_policy ifla_port_policy[IFLA_PORT_MAX+1] = { [IFLA_PORT_VF] = { .type = NLA_U32 }, [IFLA_PORT_PROFILE] = { .type = NLA_STRING, .len = PORT_PROFILE_MAX }, - [IFLA_PORT_VSI_TYPE] = { .type = NLA_BINARY, - .len = sizeof(struct ifla_port_vsi)}, [IFLA_PORT_INSTANCE_UUID] = { .type = NLA_BINARY, .len = PORT_UUID_MAX }, [IFLA_PORT_HOST_UUID] = { .type = NLA_STRING, .len = PORT_UUID_MAX }, [IFLA_PORT_REQUEST] = { .type = NLA_U8, }, [IFLA_PORT_RESPONSE] = { .type = NLA_U16, }, + + /* Unused, but we need to keep it here since user space could + * fill it. It's also broken with regard to NLA_BINARY use in + * combination with structs. + */ + [IFLA_PORT_VSI_TYPE] = { .type = NLA_BINARY, + .len = sizeof(struct ifla_port_vsi) }, }; static const struct nla_policy ifla_xdp_policy[IFLA_XDP_MAX + 1] = { @@ -2356,7 +2358,6 @@ struct net_device *rtnl_create_link(struct net *net, const char *ifname, unsigned char name_assign_type, const struct rtnl_link_ops *ops, struct nlattr *tb[]) { - int err; struct net_device *dev; unsigned int num_tx_queues = 1; unsigned int num_rx_queues = 1; @@ -2371,11 +2372,10 @@ struct net_device *rtnl_create_link(struct net *net, else if (ops->get_num_rx_queues) num_rx_queues = ops->get_num_rx_queues(); - err = -ENOMEM; dev = alloc_netdev_mqs(ops->priv_size, ifname, name_assign_type, ops->setup, num_tx_queues, num_rx_queues); if (!dev) - goto err; + return ERR_PTR(-ENOMEM); dev_net_set(dev, net); dev->rtnl_link_ops = ops; @@ -2401,9 +2401,6 @@ struct net_device *rtnl_create_link(struct net *net, dev_set_group(dev, nla_get_u32(tb[IFLA_GROUP])); return dev; - -err: - return ERR_PTR(err); } EXPORT_SYMBOL(rtnl_create_link); @@ -2571,7 +2568,7 @@ replay: return -ENODEV; } - if (tb[IFLA_MAP] || tb[IFLA_MASTER] || tb[IFLA_PROTINFO]) + if (tb[IFLA_MAP] || tb[IFLA_PROTINFO]) return -EOPNOTSUPP; if (!ops) { @@ -2653,6 +2650,11 @@ replay: if (err < 0) goto out_unregister; } + if (tb[IFLA_MASTER]) { + err = do_set_master(dev, nla_get_u32(tb[IFLA_MASTER])); + if (err) + goto out_unregister; + } out: if (link_net) put_net(link_net); @@ -3829,6 +3831,39 @@ static int rtnl_fill_statsinfo(struct sk_buff *skb, struct net_device *dev, *idxattr = 0; } + if (stats_attr_valid(filter_mask, IFLA_STATS_AF_SPEC, *idxattr)) { + struct rtnl_af_ops *af_ops; + + *idxattr = IFLA_STATS_AF_SPEC; + attr = nla_nest_start(skb, IFLA_STATS_AF_SPEC); + if (!attr) + goto nla_put_failure; + + list_for_each_entry(af_ops, &rtnl_af_ops, list) { + if (af_ops->fill_stats_af) { + struct nlattr *af; + int err; + + af = nla_nest_start(skb, af_ops->family); + if (!af) + goto nla_put_failure; + + err = af_ops->fill_stats_af(skb, dev); + + if (err == -ENODATA) + nla_nest_cancel(skb, af); + else if (err < 0) + goto nla_put_failure; + + nla_nest_end(skb, af); + } + } + + nla_nest_end(skb, attr); + + *idxattr = 0; + } + nlmsg_end(skb, nlh); return 0; @@ -3885,6 +3920,23 @@ static size_t if_nlmsg_stats_size(const struct net_device *dev, if (stats_attr_valid(filter_mask, IFLA_STATS_LINK_OFFLOAD_XSTATS, 0)) size += rtnl_get_offload_stats_size(dev); + if (stats_attr_valid(filter_mask, IFLA_STATS_AF_SPEC, 0)) { + struct rtnl_af_ops *af_ops; + + /* for IFLA_STATS_AF_SPEC */ + size += nla_total_size(0); + + list_for_each_entry(af_ops, &rtnl_af_ops, list) { + if (af_ops->get_stats_af_size) { + size += nla_total_size( + af_ops->get_stats_af_size(dev)); + + /* for AF_* */ + size += nla_total_size(0); + } + } + } + return size; } diff --git a/net/core/scm.c b/net/core/scm.c index d8820438ba37..b6d83686e149 100644 --- a/net/core/scm.c +++ b/net/core/scm.c @@ -71,7 +71,7 @@ static int scm_fp_copy(struct cmsghdr *cmsg, struct scm_fp_list **fplp) struct file **fpp; int i, num; - num = (cmsg->cmsg_len - CMSG_ALIGN(sizeof(struct cmsghdr)))/sizeof(int); + num = (cmsg->cmsg_len - sizeof(struct cmsghdr))/sizeof(int); if (num <= 0) return 0; diff --git a/net/core/secure_seq.c b/net/core/secure_seq.c index 88a8e429fc3e..758f140b6bed 100644 --- a/net/core/secure_seq.c +++ b/net/core/secure_seq.c @@ -1,3 +1,7 @@ +/* + * Copyright (C) 2016 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. + */ + #include <linux/kernel.h> #include <linux/init.h> #include <linux/cryptohash.h> @@ -8,18 +12,18 @@ #include <linux/ktime.h> #include <linux/string.h> #include <linux/net.h> - +#include <linux/siphash.h> #include <net/secure_seq.h> #if IS_ENABLED(CONFIG_IPV6) || IS_ENABLED(CONFIG_INET) +#include <linux/in6.h> #include <net/tcp.h> -#define NET_SECRET_SIZE (MD5_MESSAGE_BYTES / 4) -static u32 net_secret[NET_SECRET_SIZE] ____cacheline_aligned; +static siphash_key_t net_secret __read_mostly; static __always_inline void net_secret_init(void) { - net_get_random_once(net_secret, sizeof(net_secret)); + net_get_random_once(&net_secret, sizeof(net_secret)); } #endif @@ -44,80 +48,70 @@ static u32 seq_scale(u32 seq) u32 secure_tcpv6_sequence_number(const __be32 *saddr, const __be32 *daddr, __be16 sport, __be16 dport, u32 *tsoff) { - u32 secret[MD5_MESSAGE_BYTES / 4]; - u32 hash[MD5_DIGEST_WORDS]; - u32 i; - + const struct { + struct in6_addr saddr; + struct in6_addr daddr; + __be16 sport; + __be16 dport; + } __aligned(SIPHASH_ALIGNMENT) combined = { + .saddr = *(struct in6_addr *)saddr, + .daddr = *(struct in6_addr *)daddr, + .sport = sport, + .dport = dport + }; + u64 hash; net_secret_init(); - memcpy(hash, saddr, 16); - for (i = 0; i < 4; i++) - secret[i] = net_secret[i] + (__force u32)daddr[i]; - secret[4] = net_secret[4] + - (((__force u16)sport << 16) + (__force u16)dport); - for (i = 5; i < MD5_MESSAGE_BYTES / 4; i++) - secret[i] = net_secret[i]; - - md5_transform(hash, secret); - - *tsoff = sysctl_tcp_timestamps == 1 ? hash[1] : 0; - return seq_scale(hash[0]); + hash = siphash(&combined, offsetofend(typeof(combined), dport), + &net_secret); + *tsoff = sysctl_tcp_timestamps == 1 ? (hash >> 32) : 0; + return seq_scale(hash); } EXPORT_SYMBOL(secure_tcpv6_sequence_number); u32 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr, __be16 dport) { - u32 secret[MD5_MESSAGE_BYTES / 4]; - u32 hash[MD5_DIGEST_WORDS]; - u32 i; - + const struct { + struct in6_addr saddr; + struct in6_addr daddr; + __be16 dport; + } __aligned(SIPHASH_ALIGNMENT) combined = { + .saddr = *(struct in6_addr *)saddr, + .daddr = *(struct in6_addr *)daddr, + .dport = dport + }; net_secret_init(); - memcpy(hash, saddr, 16); - for (i = 0; i < 4; i++) - secret[i] = net_secret[i] + (__force u32) daddr[i]; - secret[4] = net_secret[4] + (__force u32)dport; - for (i = 5; i < MD5_MESSAGE_BYTES / 4; i++) - secret[i] = net_secret[i]; - - md5_transform(hash, secret); - - return hash[0]; + return siphash(&combined, offsetofend(typeof(combined), dport), + &net_secret); } EXPORT_SYMBOL(secure_ipv6_port_ephemeral); #endif #ifdef CONFIG_INET +/* secure_tcp_sequence_number(a, b, 0, d) == secure_ipv4_port_ephemeral(a, b, d), + * but fortunately, `sport' cannot be 0 in any circumstances. If this changes, + * it would be easy enough to have the former function use siphash_4u32, passing + * the arguments as separate u32. + */ + u32 secure_tcp_sequence_number(__be32 saddr, __be32 daddr, __be16 sport, __be16 dport, u32 *tsoff) { - u32 hash[MD5_DIGEST_WORDS]; - + u64 hash; net_secret_init(); - hash[0] = (__force u32)saddr; - hash[1] = (__force u32)daddr; - hash[2] = ((__force u16)sport << 16) + (__force u16)dport; - hash[3] = net_secret[15]; - - md5_transform(hash, net_secret); - - *tsoff = sysctl_tcp_timestamps == 1 ? hash[1] : 0; - return seq_scale(hash[0]); + hash = siphash_3u32((__force u32)saddr, (__force u32)daddr, + (__force u32)sport << 16 | (__force u32)dport, + &net_secret); + *tsoff = sysctl_tcp_timestamps == 1 ? (hash >> 32) : 0; + return seq_scale(hash); } u32 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport) { - u32 hash[MD5_DIGEST_WORDS]; - net_secret_init(); - hash[0] = (__force u32)saddr; - hash[1] = (__force u32)daddr; - hash[2] = (__force u32)dport ^ net_secret[14]; - hash[3] = net_secret[15]; - - md5_transform(hash, net_secret); - - return hash[0]; + return siphash_3u32((__force u32)saddr, (__force u32)daddr, + (__force u16)dport, &net_secret); } EXPORT_SYMBOL_GPL(secure_ipv4_port_ephemeral); #endif @@ -126,21 +120,13 @@ EXPORT_SYMBOL_GPL(secure_ipv4_port_ephemeral); u64 secure_dccp_sequence_number(__be32 saddr, __be32 daddr, __be16 sport, __be16 dport) { - u32 hash[MD5_DIGEST_WORDS]; u64 seq; - net_secret_init(); - hash[0] = (__force u32)saddr; - hash[1] = (__force u32)daddr; - hash[2] = ((__force u16)sport << 16) + (__force u16)dport; - hash[3] = net_secret[15]; - - md5_transform(hash, net_secret); - - seq = hash[0] | (((u64)hash[1]) << 32); + seq = siphash_3u32((__force u32)saddr, (__force u32)daddr, + (__force u32)sport << 16 | (__force u32)dport, + &net_secret); seq += ktime_get_real_ns(); seq &= (1ull << 48) - 1; - return seq; } EXPORT_SYMBOL(secure_dccp_sequence_number); @@ -149,26 +135,23 @@ EXPORT_SYMBOL(secure_dccp_sequence_number); u64 secure_dccpv6_sequence_number(__be32 *saddr, __be32 *daddr, __be16 sport, __be16 dport) { - u32 secret[MD5_MESSAGE_BYTES / 4]; - u32 hash[MD5_DIGEST_WORDS]; + const struct { + struct in6_addr saddr; + struct in6_addr daddr; + __be16 sport; + __be16 dport; + } __aligned(SIPHASH_ALIGNMENT) combined = { + .saddr = *(struct in6_addr *)saddr, + .daddr = *(struct in6_addr *)daddr, + .sport = sport, + .dport = dport + }; u64 seq; - u32 i; - net_secret_init(); - memcpy(hash, saddr, 16); - for (i = 0; i < 4; i++) - secret[i] = net_secret[i] + (__force u32)daddr[i]; - secret[4] = net_secret[4] + - (((__force u16)sport << 16) + (__force u16)dport); - for (i = 5; i < MD5_MESSAGE_BYTES / 4; i++) - secret[i] = net_secret[i]; - - md5_transform(hash, secret); - - seq = hash[0] | (((u64)hash[1]) << 32); + seq = siphash(&combined, offsetofend(typeof(combined), dport), + &net_secret); seq += ktime_get_real_ns(); seq &= (1ull << 48) - 1; - return seq; } EXPORT_SYMBOL(secure_dccpv6_sequence_number); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 734c71468b01..f3557958e9bf 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -271,7 +271,6 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, atomic_set(&fclones->fclone_ref, 1); fclones->skb2.fclone = SKB_FCLONE_CLONE; - fclones->skb2.pfmemalloc = pfmemalloc; } out: return skb; @@ -655,7 +654,7 @@ static void skb_release_head_state(struct sk_buff *skb) skb->destructor(skb); } #if IS_ENABLED(CONFIG_NF_CONNTRACK) - nf_conntrack_put(skb->nfct); + nf_conntrack_put(skb_nfct(skb)); #endif #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) nf_bridge_put(skb->nf_bridge); @@ -878,9 +877,6 @@ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old) #endif #ifdef CONFIG_NET_SCHED CHECK_SKB_FIELD(tc_index); -#ifdef CONFIG_NET_CLS_ACT - CHECK_SKB_FIELD(tc_verd); -#endif #endif } @@ -1195,10 +1191,10 @@ EXPORT_SYMBOL(__pskb_copy_fclone); int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, gfp_t gfp_mask) { - int i; - u8 *data; - int size = nhead + skb_end_offset(skb) + ntail; + int i, osize = skb_end_offset(skb); + int size = osize + nhead + ntail; long off; + u8 *data; BUG_ON(nhead < 0); @@ -1260,6 +1256,14 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, skb->hdr_len = 0; skb->nohdr = 0; atomic_set(&skb_shinfo(skb)->dataref, 1); + + /* It is not generally safe to change skb->truesize. + * For the moment, we really care of rx path, or + * when skb is orphaned (not attached to a socket). + */ + if (!skb->sk || skb->destructor == sock_edemux) + skb->truesize += size - osize; + return 0; nofrags: diff --git a/net/core/sock.c b/net/core/sock.c index 4eca27dc5c94..e7d74940e863 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -222,7 +222,7 @@ static const char *const af_family_key_strings[AF_MAX+1] = { "sk_lock-AF_RXRPC" , "sk_lock-AF_ISDN" , "sk_lock-AF_PHONET" , "sk_lock-AF_IEEE802154", "sk_lock-AF_CAIF" , "sk_lock-AF_ALG" , "sk_lock-AF_NFC" , "sk_lock-AF_VSOCK" , "sk_lock-AF_KCM" , - "sk_lock-AF_QIPCRTR", "sk_lock-AF_MAX" + "sk_lock-AF_QIPCRTR", "sk_lock-AF_SMC" , "sk_lock-AF_MAX" }; static const char *const af_family_slock_key_strings[AF_MAX+1] = { "slock-AF_UNSPEC", "slock-AF_UNIX" , "slock-AF_INET" , @@ -239,7 +239,7 @@ static const char *const af_family_slock_key_strings[AF_MAX+1] = { "slock-AF_RXRPC" , "slock-AF_ISDN" , "slock-AF_PHONET" , "slock-AF_IEEE802154", "slock-AF_CAIF" , "slock-AF_ALG" , "slock-AF_NFC" , "slock-AF_VSOCK" ,"slock-AF_KCM" , - "slock-AF_QIPCRTR", "slock-AF_MAX" + "slock-AF_QIPCRTR", "slock-AF_SMC" , "slock-AF_MAX" }; static const char *const af_family_clock_key_strings[AF_MAX+1] = { "clock-AF_UNSPEC", "clock-AF_UNIX" , "clock-AF_INET" , @@ -256,7 +256,7 @@ static const char *const af_family_clock_key_strings[AF_MAX+1] = { "clock-AF_RXRPC" , "clock-AF_ISDN" , "clock-AF_PHONET" , "clock-AF_IEEE802154", "clock-AF_CAIF" , "clock-AF_ALG" , "clock-AF_NFC" , "clock-AF_VSOCK" , "clock-AF_KCM" , - "clock-AF_QIPCRTR", "clock-AF_MAX" + "clock-AF_QIPCRTR", "clock-AF_SMC" , "clock-AF_MAX" }; /* @@ -367,7 +367,7 @@ static int sock_set_timeout(long *timeo_p, char __user *optval, int optlen) if (tv.tv_sec == 0 && tv.tv_usec == 0) return 0; if (tv.tv_sec < (MAX_SCHEDULE_TIMEOUT/HZ - 1)) - *timeo_p = tv.tv_sec*HZ + (tv.tv_usec+(1000000/HZ-1))/(1000000/HZ); + *timeo_p = tv.tv_sec * HZ + DIV_ROUND_UP(tv.tv_usec, USEC_PER_SEC / HZ); return 0; } @@ -502,6 +502,7 @@ struct dst_entry *__sk_dst_check(struct sock *sk, u32 cookie) if (dst && dst->obsolete && dst->ops->check(dst, cookie) == NULL) { sk_tx_queue_clear(sk); + sk->sk_dst_pending_confirm = 0; RCU_INIT_POINTER(sk->sk_dst_cache, NULL); dst_release(dst); return NULL; @@ -762,11 +763,8 @@ set_rcvbuf: goto set_rcvbuf; case SO_KEEPALIVE: -#ifdef CONFIG_INET - if (sk->sk_protocol == IPPROTO_TCP && - sk->sk_type == SOCK_STREAM) - tcp_set_keepalive(sk, valbool); -#endif + if (sk->sk_prot->keepalive) + sk->sk_prot->keepalive(sk, valbool); sock_valbool_flag(sk, SOCK_KEEPOPEN, valbool); break; @@ -1148,7 +1146,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname, v.tm.tv_usec = 0; } else { v.tm.tv_sec = sk->sk_rcvtimeo / HZ; - v.tm.tv_usec = ((sk->sk_rcvtimeo % HZ) * 1000000) / HZ; + v.tm.tv_usec = ((sk->sk_rcvtimeo % HZ) * USEC_PER_SEC) / HZ; } break; @@ -1159,7 +1157,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname, v.tm.tv_usec = 0; } else { v.tm.tv_sec = sk->sk_sndtimeo / HZ; - v.tm.tv_usec = ((sk->sk_sndtimeo % HZ) * 1000000) / HZ; + v.tm.tv_usec = ((sk->sk_sndtimeo % HZ) * USEC_PER_SEC) / HZ; } break; @@ -1522,6 +1520,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) af_family_clock_key_strings[newsk->sk_family]); newsk->sk_dst_cache = NULL; + newsk->sk_dst_pending_confirm = 0; newsk->sk_wmem_queued = 0; newsk->sk_forward_alloc = 0; atomic_set(&newsk->sk_drops, 0); diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index 2a46e4009f62..4ead336e14ea 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -222,6 +222,21 @@ static int set_default_qdisc(struct ctl_table *table, int write, } #endif +static int proc_do_dev_weight(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + int ret; + + ret = proc_dointvec(table, write, buffer, lenp, ppos); + if (ret != 0) + return ret; + + dev_rx_weight = weight_p * dev_weight_rx_bias; + dev_tx_weight = weight_p * dev_weight_tx_bias; + + return ret; +} + static int proc_do_rss_key(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { @@ -273,7 +288,21 @@ static struct ctl_table net_core_table[] = { .data = &weight_p, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_do_dev_weight, + }, + { + .procname = "dev_weight_rx_bias", + .data = &dev_weight_rx_bias, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_do_dev_weight, + }, + { + .procname = "dev_weight_tx_bias", + .data = &dev_weight_tx_bias, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_do_dev_weight, }, { .procname = "netdev_max_backlog", @@ -305,6 +334,13 @@ static struct ctl_table net_core_table[] = { .mode = 0600, .proc_handler = proc_dointvec, }, + { + .procname = "bpf_jit_kallsyms", + .data = &bpf_jit_kallsyms, + .maxlen = sizeof(int), + .mode = 0600, + .proc_handler = proc_dointvec, + }, # endif #endif { |