diff options
Diffstat (limited to 'net/core')
-rw-r--r-- | net/core/Makefile | 1 | ||||
-rw-r--r-- | net/core/dev.c | 138 | ||||
-rw-r--r-- | net/core/ethtool.c | 556 | ||||
-rw-r--r-- | net/core/neighbour.c | 167 | ||||
-rw-r--r-- | net/core/net-sysfs.c | 56 | ||||
-rw-r--r-- | net/core/netpoll.c | 6 | ||||
-rw-r--r-- | net/core/netprio_cgroup.c | 344 | ||||
-rw-r--r-- | net/core/pktgen.c | 15 | ||||
-rw-r--r-- | net/core/skbuff.c | 53 | ||||
-rw-r--r-- | net/core/sock.c | 33 | ||||
-rw-r--r-- | net/core/sysctl_net_core.c | 9 |
11 files changed, 767 insertions, 611 deletions
diff --git a/net/core/Makefile b/net/core/Makefile index 0d357b1..3606d40 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -19,3 +19,4 @@ obj-$(CONFIG_FIB_RULES) += fib_rules.o obj-$(CONFIG_TRACEPOINTS) += net-traces.o obj-$(CONFIG_NET_DROP_MONITOR) += drop_monitor.o obj-$(CONFIG_NETWORK_PHY_TIMESTAMPING) += timestamping.o +obj-$(CONFIG_NETPRIO_CGROUP) += netprio_cgroup.o diff --git a/net/core/dev.c b/net/core/dev.c index 6ba50a1..8afb244 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -137,6 +137,7 @@ #include <linux/if_pppox.h> #include <linux/ppp_defs.h> #include <linux/net_tstamp.h> +#include <linux/jump_label.h> #include "net-sysfs.h" @@ -1320,8 +1321,6 @@ EXPORT_SYMBOL(dev_close); */ void dev_disable_lro(struct net_device *dev) { - u32 flags; - /* * If we're trying to disable lro on a vlan device * use the underlying physical device instead @@ -1329,15 +1328,9 @@ void dev_disable_lro(struct net_device *dev) if (is_vlan_dev(dev)) dev = vlan_dev_real_dev(dev); - if (dev->ethtool_ops && dev->ethtool_ops->get_flags) - flags = dev->ethtool_ops->get_flags(dev); - else - flags = ethtool_op_get_flags(dev); + dev->wanted_features &= ~NETIF_F_LRO; + netdev_update_features(dev); - if (!(flags & ETH_FLAG_LRO)) - return; - - __ethtool_set_flags(dev, flags & ~ETH_FLAG_LRO); if (unlikely(dev->features & NETIF_F_LRO)) netdev_WARN(dev, "failed to disable LRO!\n"); } @@ -1449,34 +1442,32 @@ int call_netdevice_notifiers(unsigned long val, struct net_device *dev) } EXPORT_SYMBOL(call_netdevice_notifiers); -/* When > 0 there are consumers of rx skb time stamps */ -static atomic_t netstamp_needed = ATOMIC_INIT(0); +static struct jump_label_key netstamp_needed __read_mostly; void net_enable_timestamp(void) { - atomic_inc(&netstamp_needed); + jump_label_inc(&netstamp_needed); } EXPORT_SYMBOL(net_enable_timestamp); void net_disable_timestamp(void) { - atomic_dec(&netstamp_needed); + jump_label_dec(&netstamp_needed); } EXPORT_SYMBOL(net_disable_timestamp); static inline void net_timestamp_set(struct sk_buff *skb) { - if (atomic_read(&netstamp_needed)) + skb->tstamp.tv64 = 0; + if (static_branch(&netstamp_needed)) __net_timestamp(skb); - else - skb->tstamp.tv64 = 0; } -static inline void net_timestamp_check(struct sk_buff *skb) -{ - if (!skb->tstamp.tv64 && atomic_read(&netstamp_needed)) - __net_timestamp(skb); -} +#define net_timestamp_check(COND, SKB) \ + if (static_branch(&netstamp_needed)) { \ + if ((COND) && !(SKB)->tstamp.tv64) \ + __net_timestamp(SKB); \ + } \ static int net_hwtstamp_validate(struct ifreq *ifr) { @@ -1923,7 +1914,8 @@ EXPORT_SYMBOL(skb_checksum_help); * It may return NULL if the skb requires no segmentation. This is * only possible when GSO is used for verifying header integrity. */ -struct sk_buff *skb_gso_segment(struct sk_buff *skb, u32 features) +struct sk_buff *skb_gso_segment(struct sk_buff *skb, + netdev_features_t features) { struct sk_buff *segs = ERR_PTR(-EPROTONOSUPPORT); struct packet_type *ptype; @@ -1953,9 +1945,9 @@ struct sk_buff *skb_gso_segment(struct sk_buff *skb, u32 features) if (dev && dev->ethtool_ops && dev->ethtool_ops->get_drvinfo) dev->ethtool_ops->get_drvinfo(dev, &info); - WARN(1, "%s: caps=(0x%lx, 0x%lx) len=%d data_len=%d ip_summed=%d\n", - info.driver, dev ? dev->features : 0L, - skb->sk ? skb->sk->sk_route_caps : 0L, + WARN(1, "%s: caps=(%pNF, %pNF) len=%d data_len=%d ip_summed=%d\n", + info.driver, dev ? &dev->features : NULL, + skb->sk ? &skb->sk->sk_route_caps : NULL, skb->len, skb->data_len, skb->ip_summed); if (skb_header_cloned(skb) && @@ -2064,7 +2056,7 @@ static void dev_gso_skb_destructor(struct sk_buff *skb) * This function segments the given skb and stores the list of segments * in skb->next. */ -static int dev_gso_segment(struct sk_buff *skb, int features) +static int dev_gso_segment(struct sk_buff *skb, netdev_features_t features) { struct sk_buff *segs; @@ -2103,7 +2095,7 @@ static inline void skb_orphan_try(struct sk_buff *skb) } } -static bool can_checksum_protocol(unsigned long features, __be16 protocol) +static bool can_checksum_protocol(netdev_features_t features, __be16 protocol) { return ((features & NETIF_F_GEN_CSUM) || ((features & NETIF_F_V4_CSUM) && @@ -2114,7 +2106,8 @@ static bool can_checksum_protocol(unsigned long features, __be16 protocol) protocol == htons(ETH_P_FCOE))); } -static u32 harmonize_features(struct sk_buff *skb, __be16 protocol, u32 features) +static netdev_features_t harmonize_features(struct sk_buff *skb, + __be16 protocol, netdev_features_t features) { if (!can_checksum_protocol(features, protocol)) { features &= ~NETIF_F_ALL_CSUM; @@ -2126,10 +2119,10 @@ static u32 harmonize_features(struct sk_buff *skb, __be16 protocol, u32 features return features; } -u32 netif_skb_features(struct sk_buff *skb) +netdev_features_t netif_skb_features(struct sk_buff *skb) { __be16 protocol = skb->protocol; - u32 features = skb->dev->features; + netdev_features_t features = skb->dev->features; if (protocol == htons(ETH_P_8021Q)) { struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data; @@ -2175,7 +2168,7 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, unsigned int skb_len; if (likely(!skb->next)) { - u32 features; + netdev_features_t features; /* * If device doesn't need skb->dst, release it right now while @@ -2456,6 +2449,18 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, return rc; } +#if IS_ENABLED(CONFIG_NETPRIO_CGROUP) +static void skb_update_prio(struct sk_buff *skb) +{ + struct netprio_map *map = rcu_dereference(skb->dev->priomap); + + if ((!skb->priority) && (skb->sk) && map) + skb->priority = map->priomap[skb->sk->sk_cgrp_prioidx]; +} +#else +#define skb_update_prio(skb) +#endif + static DEFINE_PER_CPU(int, xmit_recursion); #define RECURSION_LIMIT 10 @@ -2496,6 +2501,8 @@ int dev_queue_xmit(struct sk_buff *skb) */ rcu_read_lock_bh(); + skb_update_prio(skb); + txq = dev_pick_tx(dev, skb); q = rcu_dereference_bh(txq->qdisc); @@ -2718,6 +2725,8 @@ EXPORT_SYMBOL(__skb_get_rxhash); struct rps_sock_flow_table __rcu *rps_sock_flow_table __read_mostly; EXPORT_SYMBOL(rps_sock_flow_table); +struct jump_label_key rps_needed __read_mostly; + static struct rps_dev_flow * set_rps_cpu(struct net_device *dev, struct sk_buff *skb, struct rps_dev_flow *rflow, u16 next_cpu) @@ -2997,12 +3006,11 @@ int netif_rx(struct sk_buff *skb) if (netpoll_rx(skb)) return NET_RX_DROP; - if (netdev_tstamp_prequeue) - net_timestamp_check(skb); + net_timestamp_check(netdev_tstamp_prequeue, skb); trace_netif_rx(skb); #ifdef CONFIG_RPS - { + if (static_branch(&rps_needed)) { struct rps_dev_flow voidflow, *rflow = &voidflow; int cpu; @@ -3017,14 +3025,13 @@ int netif_rx(struct sk_buff *skb) rcu_read_unlock(); preempt_enable(); - } -#else + } else +#endif { unsigned int qtail; ret = enqueue_to_backlog(skb, get_cpu(), &qtail); put_cpu(); } -#endif return ret; } EXPORT_SYMBOL(netif_rx); @@ -3230,8 +3237,7 @@ static int __netif_receive_skb(struct sk_buff *skb) int ret = NET_RX_DROP; __be16 type; - if (!netdev_tstamp_prequeue) - net_timestamp_check(skb); + net_timestamp_check(!netdev_tstamp_prequeue, skb); trace_netif_receive_skb(skb); @@ -3362,14 +3368,13 @@ out: */ int netif_receive_skb(struct sk_buff *skb) { - if (netdev_tstamp_prequeue) - net_timestamp_check(skb); + net_timestamp_check(netdev_tstamp_prequeue, skb); if (skb_defer_rx_timestamp(skb)) return NET_RX_SUCCESS; #ifdef CONFIG_RPS - { + if (static_branch(&rps_needed)) { struct rps_dev_flow voidflow, *rflow = &voidflow; int cpu, ret; @@ -3380,16 +3385,12 @@ int netif_receive_skb(struct sk_buff *skb) if (cpu >= 0) { ret = enqueue_to_backlog(skb, cpu, &rflow->last_qtail); rcu_read_unlock(); - } else { - rcu_read_unlock(); - ret = __netif_receive_skb(skb); + return ret; } - - return ret; + rcu_read_unlock(); } -#else - return __netif_receive_skb(skb); #endif + return __netif_receive_skb(skb); } EXPORT_SYMBOL(netif_receive_skb); @@ -5362,7 +5363,8 @@ static void rollback_registered(struct net_device *dev) list_del(&single); } -static u32 netdev_fix_features(struct net_device *dev, u32 features) +static netdev_features_t netdev_fix_features(struct net_device *dev, + netdev_features_t features) { /* Fix illegal checksum combinations */ if ((features & NETIF_F_HW_CSUM) && @@ -5371,12 +5373,6 @@ static u32 netdev_fix_features(struct net_device *dev, u32 features) features &= ~(NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM); } - if ((features & NETIF_F_NO_CSUM) && - (features & (NETIF_F_HW_CSUM|NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM))) { - netdev_warn(dev, "mixed no checksumming and other settings.\n"); - features &= ~(NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM|NETIF_F_HW_CSUM); - } - /* Fix illegal SG+CSUM combinations. */ if ((features & NETIF_F_SG) && !(features & NETIF_F_ALL_CSUM)) { @@ -5424,7 +5420,7 @@ static u32 netdev_fix_features(struct net_device *dev, u32 features) int __netdev_update_features(struct net_device *dev) { - u32 features; + netdev_features_t features; int err = 0; ASSERT_RTNL(); @@ -5440,16 +5436,16 @@ int __netdev_update_features(struct net_device *dev) if (dev->features == features) return 0; - netdev_dbg(dev, "Features changed: 0x%08x -> 0x%08x\n", - dev->features, features); + netdev_dbg(dev, "Features changed: %pNF -> %pNF\n", + &dev->features, &features); if (dev->netdev_ops->ndo_set_features) err = dev->netdev_ops->ndo_set_features(dev, features); if (unlikely(err < 0)) { netdev_err(dev, - "set_features() failed (%d); wanted 0x%08x, left 0x%08x\n", - err, features, dev->features); + "set_features() failed (%d); wanted %pNF, left %pNF\n", + err, &features, &dev->features); return -1; } @@ -5633,11 +5629,12 @@ int register_netdevice(struct net_device *dev) dev->wanted_features = dev->features & dev->hw_features; /* Turn on no cache copy if HW is doing checksum */ - dev->hw_features |= NETIF_F_NOCACHE_COPY; - if ((dev->features & NETIF_F_ALL_CSUM) && - !(dev->features & NETIF_F_NO_CSUM)) { - dev->wanted_features |= NETIF_F_NOCACHE_COPY; - dev->features |= NETIF_F_NOCACHE_COPY; + if (!(dev->flags & IFF_LOOPBACK)) { + dev->hw_features |= NETIF_F_NOCACHE_COPY; + if (dev->features & NETIF_F_ALL_CSUM) { + dev->wanted_features |= NETIF_F_NOCACHE_COPY; + dev->features |= NETIF_F_NOCACHE_COPY; + } } /* Make NETIF_F_HIGHDMA inheritable to VLAN devices. @@ -6373,7 +6370,8 @@ static int dev_cpu_callback(struct notifier_block *nfb, * @one to the master device with current feature set @all. Will not * enable anything that is off in @mask. Returns the new feature set. */ -u32 netdev_increment_features(u32 all, u32 one, u32 mask) +netdev_features_t netdev_increment_features(netdev_features_t all, + netdev_features_t one, netdev_features_t mask) { if (mask & NETIF_F_GEN_CSUM) mask |= NETIF_F_ALL_CSUM; @@ -6382,10 +6380,6 @@ u32 netdev_increment_features(u32 all, u32 one, u32 mask) all |= one & (NETIF_F_ONE_FOR_ALL|NETIF_F_ALL_CSUM) & mask; all &= one | ~NETIF_F_ALL_FOR_ALL; - /* If device needs checksumming, downgrade to it. */ - if (all & (NETIF_F_ALL_CSUM & ~NETIF_F_NO_CSUM)) - all &= ~NETIF_F_NO_CSUM; - /* If one device supports hw checksumming, set for all. */ if (all & NETIF_F_GEN_CSUM) all &= ~(NETIF_F_ALL_CSUM & ~NETIF_F_GEN_CSUM); diff --git a/net/core/ethtool.c b/net/core/ethtool.c index f444817..31b0b7f 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -36,235 +36,44 @@ u32 ethtool_op_get_link(struct net_device *dev) } EXPORT_SYMBOL(ethtool_op_get_link); -u32 ethtool_op_get_tx_csum(struct net_device *dev) -{ - return (dev->features & NETIF_F_ALL_CSUM) != 0; -} -EXPORT_SYMBOL(ethtool_op_get_tx_csum); - -int ethtool_op_set_tx_csum(struct net_device *dev, u32 data) -{ - if (data) - dev->features |= NETIF_F_IP_CSUM; - else - dev->features &= ~NETIF_F_IP_CSUM; - - return 0; -} -EXPORT_SYMBOL(ethtool_op_set_tx_csum); - -int ethtool_op_set_tx_hw_csum(struct net_device *dev, u32 data) -{ - if (data) - dev->features |= NETIF_F_HW_CSUM; - else - dev->features &= ~NETIF_F_HW_CSUM; - - return 0; -} -EXPORT_SYMBOL(ethtool_op_set_tx_hw_csum); - -int ethtool_op_set_tx_ipv6_csum(struct net_device *dev, u32 data) -{ - if (data) - dev->features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM; - else - dev->features &= ~(NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM); - - return 0; -} -EXPORT_SYMBOL(ethtool_op_set_tx_ipv6_csum); - -u32 ethtool_op_get_sg(struct net_device *dev) -{ - return (dev->features & NETIF_F_SG) != 0; -} -EXPORT_SYMBOL(ethtool_op_get_sg); - -int ethtool_op_set_sg(struct net_device *dev, u32 data) -{ - if (data) - dev->features |= NETIF_F_SG; - else - dev->features &= ~NETIF_F_SG; - - return 0; -} -EXPORT_SYMBOL(ethtool_op_set_sg); - -u32 ethtool_op_get_tso(struct net_device *dev) -{ - return (dev->features & NETIF_F_TSO) != 0; -} -EXPORT_SYMBOL(ethtool_op_get_tso); - -int ethtool_op_set_tso(struct net_device *dev, u32 data) -{ - if (data) - dev->features |= NETIF_F_TSO; - else - dev->features &= ~NETIF_F_TSO; - - return 0; -} -EXPORT_SYMBOL(ethtool_op_set_tso); - -u32 ethtool_op_get_ufo(struct net_device *dev) -{ - return (dev->features & NETIF_F_UFO) != 0; -} -EXPORT_SYMBOL(ethtool_op_get_ufo); - -int ethtool_op_set_ufo(struct net_device *dev, u32 data) -{ - if (data) - dev->features |= NETIF_F_UFO; - else - dev->features &= ~NETIF_F_UFO; - return 0; -} -EXPORT_SYMBOL(ethtool_op_set_ufo); - -/* the following list of flags are the same as their associated - * NETIF_F_xxx values in include/linux/netdevice.h - */ -static const u32 flags_dup_features = - (ETH_FLAG_LRO | ETH_FLAG_RXVLAN | ETH_FLAG_TXVLAN | ETH_FLAG_NTUPLE | - ETH_FLAG_RXHASH); - -u32 ethtool_op_get_flags(struct net_device *dev) -{ - /* in the future, this function will probably contain additional - * handling for flags which are not so easily handled - * by a simple masking operation - */ - - return dev->features & flags_dup_features; -} -EXPORT_SYMBOL(ethtool_op_get_flags); - -/* Check if device can enable (or disable) particular feature coded in "data" - * argument. Flags "supported" describe features that can be toggled by device. - * If feature can not be toggled, it state (enabled or disabled) must match - * hardcoded device features state, otherwise flags are marked as invalid. - */ -bool ethtool_invalid_flags(struct net_device *dev, u32 data, u32 supported) -{ - u32 features = dev->features & flags_dup_features; - /* "data" can contain only flags_dup_features bits, - * see __ethtool_set_flags */ - - return (features & ~supported) != (data & ~supported); -} -EXPORT_SYMBOL(ethtool_invalid_flags); - -int ethtool_op_set_flags(struct net_device *dev, u32 data, u32 supported) -{ - if (ethtool_invalid_flags(dev, data, supported)) - return -EINVAL; - - dev->features = ((dev->features & ~flags_dup_features) | - (data & flags_dup_features)); - return 0; -} -EXPORT_SYMBOL(ethtool_op_set_flags); - /* Handlers for each ethtool command */ -#define ETHTOOL_DEV_FEATURE_WORDS 1 - -static void ethtool_get_features_compat(struct net_device *dev, - struct ethtool_get_features_block *features) -{ - if (!dev->ethtool_ops) - return; - - /* getting RX checksum */ - if (dev->ethtool_ops->get_rx_csum) - if (dev->ethtool_ops->get_rx_csum(dev)) - features[0].active |= NETIF_F_RXCSUM; - - /* mark legacy-changeable features */ - if (dev->ethtool_ops->set_sg) - features[0].available |= NETIF_F_SG; - if (dev->ethtool_ops->set_tx_csum) - features[0].available |= NETIF_F_ALL_CSUM; - if (dev->ethtool_ops->set_tso) - features[0].available |= NETIF_F_ALL_TSO; - if (dev->ethtool_ops->set_rx_csum) - features[0].available |= NETIF_F_RXCSUM; - if (dev->ethtool_ops->set_flags) - features[0].available |= flags_dup_features; -} - -static int ethtool_set_feature_compat(struct net_device *dev, - int (*legacy_set)(struct net_device *, u32), - struct ethtool_set_features_block *features, u32 mask) -{ - u32 do_set; - - if (!legacy_set) - return 0; - - if (!(features[0].valid & mask)) - return 0; - - features[0].valid &= ~mask; - - do_set = !!(features[0].requested & mask); - - if (legacy_set(dev, do_set) < 0) - netdev_info(dev, - "Legacy feature change (%s) failed for 0x%08x\n", - do_set ? "set" : "clear", mask); - - return 1; -} - -static int ethtool_set_flags_compat(struct net_device *dev, - int (*legacy_set)(struct net_device *, u32), - struct ethtool_set_features_block *features, u32 mask) -{ - u32 value; - - if (!legacy_set) - return 0; - - if (!(features[0].valid & mask)) - return 0; - - value = dev->features & ~features[0].valid; - value |= features[0].requested; - - features[0].valid &= ~mask; - - if (legacy_set(dev, value & mask) < 0) - netdev_info(dev, "Legacy flags change failed\n"); - - return 1; -} - -static int ethtool_set_features_compat(struct net_device *dev, - struct ethtool_set_features_block *features) -{ - int compat; - - if (!dev->ethtool_ops) - return 0; - - compat = ethtool_set_feature_compat(dev, dev->ethtool_ops->set_sg, - features, NETIF_F_SG); - compat |= ethtool_set_feature_compat(dev, dev->ethtool_ops->set_tx_csum, - features, NETIF_F_ALL_CSUM); - compat |= ethtool_set_feature_compat(dev, dev->ethtool_ops->set_tso, - features, NETIF_F_ALL_TSO); - compat |= ethtool_set_feature_compat(dev, dev->ethtool_ops->set_rx_csum, - features, NETIF_F_RXCSUM); - compat |= ethtool_set_flags_compat(dev, dev->ethtool_ops->set_flags, - features, flags_dup_features); - - return compat; -} +#define ETHTOOL_DEV_FEATURE_WORDS ((NETDEV_FEATURE_COUNT + 31) / 32) + +static const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN] = { + [NETIF_F_SG_BIT] = "tx-scatter-gather", + [NETIF_F_IP_CSUM_BIT] = "tx-checksum-ipv4", + [NETIF_F_HW_CSUM_BIT] = "tx-checksum-ip-generic", + [NETIF_F_IPV6_CSUM_BIT] = "tx-checksum-ipv6", + [NETIF_F_HIGHDMA_BIT] = "highdma", + [NETIF_F_FRAGLIST_BIT] = "tx-scatter-gather-fraglist", + [NETIF_F_HW_VLAN_TX_BIT] = "tx-vlan-hw-insert", + + [NETIF_F_HW_VLAN_RX_BIT] = "rx-vlan-hw-parse", + [NETIF_F_HW_VLAN_FILTER_BIT] = "rx-vlan-filter", + [NETIF_F_VLAN_CHALLENGED_BIT] = "vlan-challenged", + [NETIF_F_GSO_BIT] = "tx-generic-segmentation", + [NETIF_F_LLTX_BIT] = "tx-lockless", + [NETIF_F_NETNS_LOCAL_BIT] = "netns-local", + [NETIF_F_GRO_BIT] = "rx-gro", + [NETIF_F_LRO_BIT] = "rx-lro", + + [NETIF_F_TSO_BIT] = "tx-tcp-segmentation", + [NETIF_F_UFO_BIT] = "tx-udp-fragmentation", + [NETIF_F_GSO_ROBUST_BIT] = "tx-gso-robust", + [NETIF_F_TSO_ECN_BIT] = "tx-tcp-ecn-segmentation", + [NETIF_F_TSO6_BIT] = "tx-tcp6-segmentation", + [NETIF_F_FSO_BIT] = "tx-fcoe-segmentation", + + [NETIF_F_FCOE_CRC_BIT] = "tx-checksum-fcoe-crc", + [NETIF_F_SCTP_CSUM_BIT] = "tx-checksum-sctp", + [NETIF_F_FCOE_MTU_BIT] = "fcoe-mtu", + [NETIF_F_NTUPLE_BIT] = "rx-ntuple-filter", + [NETIF_F_RXHASH_BIT] = "rx-hashing", + [NETIF_F_RXCSUM_BIT] = "rx-checksum", + [NETIF_F_NOCACHE_COPY_BIT] = "tx-nocache-copy", + [NETIF_F_LOOPBACK_BIT] = "loopback", +}; static int ethtool_get_features(struct net_device *dev, void __user *useraddr) { @@ -272,18 +81,21 @@ static int ethtool_get_features(struct net_device *dev, void __user *useraddr) .cmd = ETHTOOL_GFEATURES, .size = ETHTOOL_DEV_FEATURE_WORDS, }; - struct ethtool_get_features_block features[ETHTOOL_DEV_FEATURE_WORDS] = { - { - .available = dev->hw_features, - .requested = dev->wanted_features, - .active = dev->features, - .never_changed = NETIF_F_NEVER_CHANGE, - }, - }; + struct ethtool_get_features_block features[ETHTOOL_DEV_FEATURE_WORDS]; u32 __user *sizeaddr; u32 copy_size; + int i; - ethtool_get_features_compat(dev, features); + /* in case feature bits run out again */ + BUILD_BUG_ON(ETHTOOL_DEV_FEATURE_WORDS * sizeof(u32) > sizeof(netdev_features_t)); + + for (i = 0; i < ETHTOOL_DEV_FEATURE_WORDS; ++i) { + features[i].available = (u32)(dev->hw_features >> (32 * i)); + features[i].requested = (u32)(dev->wanted_features >> (32 * i)); + features[i].active = (u32)(dev->features >> (32 * i)); + features[i].never_changed = + (u32)(NETIF_F_NEVER_CHANGE >> (32 * i)); + } sizeaddr = useraddr + offsetof(struct ethtool_gfeatures, size); if (get_user(copy_size, sizeaddr)) @@ -305,7 +117,8 @@ static int ethtool_set_features(struct net_device *dev, void __user *useraddr) { struct ethtool_sfeatures cmd; struct ethtool_set_features_block features[ETHTOOL_DEV_FEATURE_WORDS]; - int ret = 0; + netdev_features_t wanted = 0, valid = 0; + int i, ret = 0; if (copy_from_user(&cmd, useraddr, sizeof(cmd))) return -EFAULT; @@ -317,65 +130,29 @@ static int ethtool_set_features(struct net_device *dev, void __user *useraddr) if (copy_from_user(features, useraddr, sizeof(features))) return -EFAULT; - if (features[0].valid & ~NETIF_F_ETHTOOL_BITS) - return -EINVAL; + for (i = 0; i < ETHTOOL_DEV_FEATURE_WORDS; ++i) { + valid |= (netdev_features_t)features[i].valid << (32 * i); + wanted |= (netdev_features_t)features[i].requested << (32 * i); + } - if (ethtool_set_features_compat(dev, features)) - ret |= ETHTOOL_F_COMPAT; + if (valid & ~NETIF_F_ETHTOOL_BITS) + return -EINVAL; - if (features[0].valid & ~dev->hw_features) { - features[0].valid &= dev->hw_features; + if (valid & ~dev->hw_features) { + valid &= dev->hw_features; ret |= ETHTOOL_F_UNSUPPORTED; } - dev->wanted_features &= ~features[0].valid; - dev->wanted_features |= features[0].valid & features[0].requested; + dev->wanted_features &= ~valid; + dev->wanted_features |= wanted & valid; __netdev_update_features(dev); - if ((dev->wanted_features ^ dev->features) & features[0].valid) + if ((dev->wanted_features ^ dev->features) & valid) ret |= ETHTOOL_F_WISH; return ret; } -static const char netdev_features_strings[ETHTOOL_DEV_FEATURE_WORDS * 32][ETH_GSTRING_LEN] = { - /* NETIF_F_SG */ "tx-scatter-gather", - /* NETIF_F_IP_CSUM */ "tx-checksum-ipv4", - /* NETIF_F_NO_CSUM */ "tx-checksum-unneeded", - /* NETIF_F_HW_CSUM */ "tx-checksum-ip-generic", - /* NETIF_F_IPV6_CSUM */ "tx-checksum-ipv6", - /* NETIF_F_HIGHDMA */ "highdma", - /* NETIF_F_FRAGLIST */ "tx-scatter-gather-fraglist", - /* NETIF_F_HW_VLAN_TX */ "tx-vlan-hw-insert", - - /* NETIF_F_HW_VLAN_RX */ "rx-vlan-hw-parse", - /* NETIF_F_HW_VLAN_FILTER */ "rx-vlan-filter", - /* NETIF_F_VLAN_CHALLENGED */ "vlan-challenged", - /* NETIF_F_GSO */ "tx-generic-segmentation", - /* NETIF_F_LLTX */ "tx-lockless", - /* NETIF_F_NETNS_LOCAL */ "netns-local", - /* NETIF_F_GRO */ "rx-gro", - /* NETIF_F_LRO */ "rx-lro", - - /* NETIF_F_TSO */ "tx-tcp-segmentation", - /* NETIF_F_UFO */ "tx-udp-fragmentation", - /* NETIF_F_GSO_ROBUST */ "tx-gso-robust", - /* NETIF_F_TSO_ECN */ "tx-tcp-ecn-segmentation", - /* NETIF_F_TSO6 */ "tx-tcp6-segmentation", - /* NETIF_F_FSO */ "tx-fcoe-segmentation", - "", - "", - - /* NETIF_F_FCOE_CRC */ "tx-checksum-fcoe-crc", - /* NETIF_F_SCTP_CSUM */ "tx-checksum-sctp", - /* NETIF_F_FCOE_MTU */ "fcoe-mtu", - /* NETIF_F_NTUPLE */ "rx-ntuple-filter", - /* NETIF_F_RXHASH */ "rx-hashing", - /* NETIF_F_RXCSUM */ "rx-checksum", - /* NETIF_F_NOCACHE_COPY */ "tx-nocache-copy", - /* NETIF_F_LOOPBACK */ "loopback", -}; - static int __ethtool_get_sset_count(struct net_device *dev, int sset) { const struct ethtool_ops *ops = dev->ethtool_ops; @@ -402,7 +179,7 @@ static void __ethtool_get_strings(struct net_device *dev, ops->get_strings(dev, stringset, data); } -static u32 ethtool_get_feature_mask(u32 eth_cmd) +static netdev_features_t ethtool_get_feature_mask(u32 eth_cmd) { /* feature masks of legacy discrete ethtool ops */ @@ -433,136 +210,82 @@ static u32 ethtool_get_feature_mask(u32 eth_cmd) } } -static void *__ethtool_get_one_feature_actor(struct net_device *dev, u32 ethcmd) -{ - const struct ethtool_ops *ops = dev->ethtool_ops; - - if (!ops) - return NULL; - - switch (ethcmd) { - case ETHTOOL_GTXCSUM: - return ops->get_tx_csum; - case ETHTOOL_GRXCSUM: - return ops->get_rx_csum; - case ETHTOOL_SSG: - return ops->get_sg; - case ETHTOOL_STSO: - return ops->get_tso; - case ETHTOOL_SUFO: - return ops->get_ufo; - default: - return NULL; - } -} - -static u32 __ethtool_get_rx_csum_oldbug(struct net_device *dev) -{ - return !!(dev->features & NETIF_F_ALL_CSUM); -} - static int ethtool_get_one_feature(struct net_device *dev, char __user *useraddr, u32 ethcmd) { - u32 mask = ethtool_get_feature_mask(ethcmd); + netdev_features_t mask = ethtool_get_feature_mask(ethcmd); struct ethtool_value edata = { .cmd = ethcmd, .data = !!(dev->features & mask), }; - /* compatibility with discrete get_ ops */ - if (!(dev->hw_features & mask)) { - u32 (*actor)(struct net_device *); - - actor = __ethtool_get_one_feature_actor(dev, ethcmd); - - /* bug compatibility with old get_rx_csum */ - if (ethcmd == ETHTOOL_GRXCSUM && !actor) - actor = __ethtool_get_rx_csum_oldbug; - - if (actor) - edata.data = actor(dev); - } - if (copy_to_user(useraddr, &edata, sizeof(edata))) return -EFAULT; return 0; } -static int __ethtool_set_tx_csum(struct net_device *dev, u32 data); -static int __ethtool_set_rx_csum(struct net_device *dev, u32 data); -static int __ethtool_set_sg(struct net_device *dev, u32 data); -static int __ethtool_set_tso(struct net_device *dev, u32 data); -static int __ethtool_set_ufo(struct net_device *dev, u32 data); - static int ethtool_set_one_feature(struct net_device *dev, void __user *useraddr, u32 ethcmd) { struct ethtool_value edata; - u32 mask; + netdev_features_t mask; if (copy_from_user(&edata, useraddr, sizeof(edata))) return -EFAULT; mask = ethtool_get_feature_mask(ethcmd); mask &= dev->hw_features; - if (mask) { - if (edata.data) - dev->wanted_features |= mask; - else - dev->wanted_features &= ~mask; + if (!mask) + return -EOPNOTSUPP; - __netdev_update_features(dev); - return 0; - } + if (edata.data) + dev->wanted_features |= mask; + else + dev->wanted_features &= ~mask; - /* Driver is not converted to ndo_fix_features or does not - * support changing this offload. In the latter case it won't - * have corresponding ethtool_ops field set. - * - * Following part is to be removed after all drivers advertise - * their changeable features in netdev->hw_features and stop - * using discrete offload setting ops. - */ + __netdev_update_features(dev); - switch (ethcmd) { - case ETHTOOL_STXCSUM: - return __ethtool_set_tx_csum(dev, edata.data); - case ETHTOOL_SRXCSUM: - return __ethtool_set_rx_csum(dev, edata.data); - case ETHTOOL_SSG: - return __ethtool_set_sg(dev, edata.data); - case ETHTOOL_STSO: - return __ethtool_set_tso(dev, edata.data); - case ETHTOOL_SUFO: - return __ethtool_set_ufo(dev, edata.data); - default: - return -EOPNOTSUPP; - } + return 0; +} + +#define ETH_ALL_FLAGS (ETH_FLAG_LRO | ETH_FLAG_RXVLAN | ETH_FLAG_TXVLAN | \ + ETH_FLAG_NTUPLE | ETH_FLAG_RXHASH) +#define ETH_ALL_FEATURES (NETIF_F_LRO | NETIF_F_HW_VLAN_RX | \ + NETIF_F_HW_VLAN_TX | NETIF_F_NTUPLE | NETIF_F_RXHASH) + +static u32 __ethtool_get_flags(struct net_device *dev) +{ + u32 flags = 0; + + if (dev->features & NETIF_F_LRO) flags |= ETH_FLAG_LRO; + if (dev->features & NETIF_F_HW_VLAN_RX) flags |= ETH_FLAG_RXVLAN; + if (dev->features & NETIF_F_HW_VLAN_TX) flags |= ETH_FLAG_TXVLAN; + if (dev->features & NETIF_F_NTUPLE) flags |= ETH_FLAG_NTUPLE; + if (dev->features & NETIF_F_RXHASH) flags |= ETH_FLAG_RXHASH; + + return flags; } -int __ethtool_set_flags(struct net_device *dev, u32 data) +static int __ethtool_set_flags(struct net_device *dev, u32 data) { - u32 changed; + netdev_features_t features = 0, changed; - if (data & ~flags_dup_features) + if (data & ~ETH_ALL_FLAGS) return -EINVAL; - /* legacy set_flags() op */ - if (dev->ethtool_ops->set_flags) { - if (unlikely(dev->hw_features & flags_dup_features)) - netdev_warn(dev, - "driver BUG: mixed hw_features and set_flags()\n"); - return dev->ethtool_ops->set_flags(dev, data); - } + if (data & ETH_FLAG_LRO) features |= NETIF_F_LRO; + if (data & ETH_FLAG_RXVLAN) features |= NETIF_F_HW_VLAN_RX; + if (data & ETH_FLAG_TXVLAN) features |= NETIF_F_HW_VLAN_TX; + if (data & ETH_FLAG_NTUPLE) features |= NETIF_F_NTUPLE; + if (data & ETH_FLAG_RXHASH) features |= NETIF_F_RXHASH; /* allow changing only bits set in hw_features */ - changed = (data ^ dev->features) & flags_dup_features; + changed = (features ^ dev->features) & ETH_ALL_FEATURES; if (changed & ~dev->hw_features) return (changed & dev->hw_features) ? -EINVAL : -EOPNOTSUPP; dev->wanted_features = - (dev->wanted_features & ~changed) | (data & dev->hw_features); + (dev->wanted_features & ~changed) | (features & changed); __netdev_update_features(dev); @@ -1231,81 +954,6 @@ static int ethtool_set_pauseparam(struct net_device *dev, void __user *useraddr) return dev->ethtool_ops->set_pauseparam(dev, &pauseparam); } -static int __ethtool_set_sg(struct net_device *dev, u32 data) -{ - int err; - - if (!dev->ethtool_ops->set_sg) - return -EOPNOTSUPP; - - if (data && !(dev->features & NETIF_F_ALL_CSUM)) - return -EINVAL; - - if (!data && dev->ethtool_ops->set_tso) { - err = dev->ethtool_ops->set_tso(dev, 0); - if (err) - return err; - } - - if (!data && dev->ethtool_ops->set_ufo) { - err = dev->ethtool_ops->set_ufo(dev, 0); - if (err) - return err; - } - return dev->ethtool_ops->set_sg(dev, data); -} - -static int __ethtool_set_tx_csum(struct net_device *dev, u32 data) -{ - int err; - - if (!dev->ethtool_ops->set_tx_csum) - return -EOPNOTSUPP; - - if (!data && dev->ethtool_ops->set_sg) { - err = __ethtool_set_sg(dev, 0); - if (err) - return err; - } - - return dev->ethtool_ops->set_tx_csum(dev, data); -} - -static int __ethtool_set_rx_csum(struct net_device *dev, u32 data) -{ - if (!dev->ethtool_ops->set_rx_csum) - return -EOPNOTSUPP; - - if (!data) - dev->features &= ~NETIF_F_GRO; - - return dev->ethtool_ops->set_rx_csum(dev, data); -} - -static int __ethtool_set_tso(struct net_device *dev, u32 data) -{ - if (!dev->ethtool_ops->set_tso) - return -EOPNOTSUPP; - - if (data && !(dev->features & NETIF_F_SG)) - return -EINVAL; - - return dev->ethtool_ops->set_tso(dev, data); -} - -static int __ethtool_set_ufo(struct net_device *dev, u32 data) -{ - if (!dev->ethtool_ops->set_ufo) - return -EOPNOTSUPP; - if (data && !(dev->features & NETIF_F_SG)) - return -EINVAL; - if (data && !((dev->features & NETIF_F_GEN_CSUM) || - (dev->features & (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM)) - == (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM))) - return -EINVAL; - return dev->ethtool_ops->set_ufo(dev, data); -} - static int ethtool_self_test(struct net_device *dev, char __user *useraddr) { struct ethtool_test test; @@ -1771,9 +1419,7 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) break; case ETHTOOL_GFLAGS: rc = ethtool_get_value(dev, useraddr, ethcmd, - (dev->ethtool_ops->get_flags ? - dev->ethtool_ops->get_flags : - ethtool_op_get_flags)); + __ethtool_get_flags); break; case ETHTOOL_SFLAGS: rc = ethtool_set_value(dev, useraddr, __ethtool_set_flags); diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 039d51e..27d3fef 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -238,6 +238,7 @@ static void neigh_flush_dev(struct neigh_table *tbl, struct net_device *dev) it to safe state. */ skb_queue_purge(&n->arp_queue); + n->arp_queue_len_bytes = 0; n->output = neigh_blackhole; if (n->nud_state & NUD_VALID) n->nud_state = NUD_NOARP; @@ -702,6 +703,7 @@ void neigh_destroy(struct neighbour *neigh) printk(KERN_WARNING "Impossible event.\n"); skb_queue_purge(&neigh->arp_queue); + neigh->arp_queue_len_bytes = 0; dev_put(neigh->dev); neigh_parms_put(neigh->parms); @@ -842,6 +844,7 @@ static void neigh_invalidate(struct neighbour *neigh) write_lock(&neigh->lock); } skb_queue_purge(&neigh->arp_queue); + neigh->arp_queue_len_bytes = 0; } static void neigh_probe(struct neighbour *neigh) @@ -980,15 +983,20 @@ int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb) if (neigh->nud_state == NUD_INCOMPLETE) { if (skb) { - if (skb_queue_len(&neigh->arp_queue) >= - neigh->parms->queue_len) { + while (neigh->arp_queue_len_bytes + skb->truesize > + neigh->parms->queue_len_bytes) { struct sk_buff *buff; + buff = __skb_dequeue(&neigh->arp_queue); + if (!buff) + break; + neigh->arp_queue_len_bytes -= buff->truesize; kfree_skb(buff); NEIGH_CACHE_STAT_INC(neigh->tbl, unres_discards); } skb_dst_force(skb); __skb_queue_tail(&neigh->arp_queue, skb); + neigh->arp_queue_len_bytes += skb->truesize; } rc = 1; } @@ -1175,6 +1183,7 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, write_lock_bh(&neigh->lock); } skb_queue_purge(&neigh->arp_queue); + neigh->arp_queue_len_bytes = 0; } out: if (update_isrouter) { @@ -1747,7 +1756,11 @@ static int neightbl_fill_parms(struct sk_buff *skb, struct neigh_parms *parms) NLA_PUT_U32(skb, NDTPA_IFINDEX, parms->dev->ifindex); NLA_PUT_U32(skb, NDTPA_REFCNT, atomic_read(&parms->refcnt)); - NLA_PUT_U32(skb, NDTPA_QUEUE_LEN, parms->queue_len); + NLA_PUT_U32(skb, NDTPA_QUEUE_LENBYTES, parms->queue_len_bytes); + /* approximative value for deprecated QUEUE_LEN (in packets) */ + NLA_PUT_U32(skb, NDTPA_QUEUE_LEN, + DIV_ROUND_UP(parms->queue_len_bytes, + SKB_TRUESIZE(ETH_FRAME_LEN))); NLA_PUT_U32(skb, NDTPA_PROXY_QLEN, parms->proxy_qlen); NLA_PUT_U32(skb, NDTPA_APP_PROBES, parms->app_probes); NLA_PUT_U32(skb, NDTPA_UCAST_PROBES, parms->ucast_probes); @@ -1974,7 +1987,11 @@ static int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) switch (i) { case NDTPA_QUEUE_LEN: - p->queue_len = nla_get_u32(tbp[i]); + p->queue_len_bytes = nla_get_u32(tbp[i]) * + SKB_TRUESIZE(ETH_FRAME_LEN); + break; + case NDTPA_QUEUE_LENBYTES: + p->queue_len_bytes = nla_get_u32(tbp[i]); break; case NDTPA_PROXY_QLEN: p->proxy_qlen = nla_get_u32(tbp[i]); @@ -2397,7 +2414,10 @@ static struct pneigh_entry *pneigh_get_next(struct seq_file *seq, struct net *net = seq_file_net(seq); struct neigh_table *tbl = state->tbl; - pn = pn->next; + do { + pn = pn->next; + } while (pn && !net_eq(pneigh_net(pn), net)); + while (!pn) { if (++state->bucket > PNEIGH_HASHMASK) break; @@ -2635,117 +2655,158 @@ EXPORT_SYMBOL(neigh_app_ns); #ifdef CONFIG_SYSCTL -#define NEIGH_VARS_MAX 19 +static int proc_unres_qlen(ctl_table *ctl, int write, void __user *buffer, + size_t *lenp, loff_t *ppos) +{ + int size, ret; + ctl_table tmp = *ctl; + + tmp.data = &size; + size = DIV_ROUND_UP(*(int *)ctl->data, SKB_TRUESIZE(ETH_FRAME_LEN)); + ret = proc_dointvec(&tmp, write, buffer, lenp, ppos); + if (write && !ret) + *(int *)ctl->data = size * SKB_TRUESIZE(ETH_FRAME_LEN); + return ret; +} + +enum { + NEIGH_VAR_MCAST_PROBE, + NEIGH_VAR_UCAST_PROBE, + NEIGH_VAR_APP_PROBE, + NEIGH_VAR_RETRANS_TIME, + NEIGH_VAR_BASE_REACHABLE_TIME, + NEIGH_VAR_DELAY_PROBE_TIME, + NEIGH_VAR_GC_STALETIME, + NEIGH_VAR_QUEUE_LEN, + NEIGH_VAR_QUEUE_LEN_BYTES, + NEIGH_VAR_PROXY_QLEN, + NEIGH_VAR_ANYCAST_DELAY, + NEIGH_VAR_PROXY_DELAY, + NEIGH_VAR_LOCKTIME, + NEIGH_VAR_RETRANS_TIME_MS, + NEIGH_VAR_BASE_REACHABLE_TIME_MS, + NEIGH_VAR_GC_INTERVAL, + NEIGH_VAR_GC_THRESH1, + NEIGH_VAR_GC_THRESH2, + NEIGH_VAR_GC_THRESH3, + NEIGH_VAR_MAX +}; static struct neigh_sysctl_table { struct ctl_table_header *sysctl_header; - struct ctl_table neigh_vars[NEIGH_VARS_MAX]; + struct ctl_table neigh_vars[NEIGH_VAR_MAX + 1]; char *dev_name; } neigh_sysctl_template __read_mostly = { .neigh_vars = { - { + [NEIGH_VAR_MCAST_PROBE] = { .procname = "mcast_solicit", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, - { + [NEIGH_VAR_UCAST_PROBE] = { .procname = "ucast_solicit", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, - { + [NEIGH_VAR_APP_PROBE] = { .procname = "app_solicit", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, - { + [NEIGH_VAR_RETRANS_TIME] = { .procname = "retrans_time", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_userhz_jiffies, }, - { + [NEIGH_VAR_BASE_REACHABLE_TIME] = { .procname = "base_reachable_time", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, - { + [NEIGH_VAR_DELAY_PROBE_TIME] = { .procname = "delay_first_probe_time", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, - { + [NEIGH_VAR_GC_STALETIME] = { .procname = "gc_stale_time", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, - { + [NEIGH_VAR_QUEUE_LEN] = { .procname = "unres_qlen", .maxlen = sizeof(int), .mode = 0644, + .proc_handler = proc_unres_qlen, + }, + [NEIGH_VAR_QUEUE_LEN_BYTES] = { + .procname = "unres_qlen_bytes", + .maxlen = sizeof(int), + .mode = 0644, .proc_handler = proc_dointvec, }, - { + [NEIGH_VAR_PROXY_QLEN] = { .procname = "proxy_qlen", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, - { + [NEIGH_VAR_ANYCAST_DELAY] = { .procname = "anycast_delay", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_userhz_jiffies, }, - { + [NEIGH_VAR_PROXY_DELAY] = { .procname = "proxy_delay", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_userhz_jiffies, }, - { + [NEIGH_VAR_LOCKTIME] = { .procname = "locktime", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_userhz_jiffies, }, - { + [NEIGH_VAR_RETRANS_TIME_MS] = { .procname = "retrans_time_ms", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_ms_jiffies, }, - { + [NEIGH_VAR_BASE_REACHABLE_TIME_MS] = { .procname = "base_reachable_time_ms", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_ms_jiffies, }, - { + [NEIGH_VAR_GC_INTERVAL] = { .procname = "gc_interval", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, - { + [NEIGH_VAR_GC_THRESH1] = { .procname = "gc_thresh1", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, - { + [NEIGH_VAR_GC_THRESH2] = { .procname = "gc_thresh2", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, - { + [NEIGH_VAR_GC_THRESH3] = { .procname = "gc_thresh3", .maxlen = sizeof(int), .mode = 0644, @@ -2778,47 +2839,49 @@ int neigh_sysctl_register(struct net_device *dev, struct neigh_parms *p, if (!t) goto err; - t->neigh_vars[0].data = &p->mcast_probes; - t->neigh_vars[1].data = &p->ucast_probes; - t->neigh_vars[2].data = &p->app_probes; - t->neigh_vars[3].data = &p->retrans_time; - t->neigh_vars[4].data = &p->base_reachable_time; - t->neigh_vars[5].data = &p->delay_probe_time; - t->neigh_vars[6].data = &p->gc_staletime; - t->neigh_vars[7].data = &p->queue_len; - t->neigh_vars[8].data = &p->proxy_qlen; - t->neigh_vars[9].data = &p->anycast_delay; - t->neigh_vars[10].data = &p->proxy_delay; - t->neigh_vars[11].data = &p->locktime; - t->neigh_vars[12].data = &p->retrans_time; - t->neigh_vars[13].data = &p->base_reachable_time; + t->neigh_vars[NEIGH_VAR_MCAST_PROBE].data = &p->mcast_probes; + t->neigh_vars[NEIGH_VAR_UCAST_PROBE].data = &p->ucast_probes; + t->neigh_vars[NEIGH_VAR_APP_PROBE].data = &p->app_probes; + t->neigh_vars[NEIGH_VAR_RETRANS_TIME].data = &p->retrans_time; + t->neigh_vars[NEIGH_VAR_BASE_REACHABLE_TIME].data = &p->base_reachable_time; + t->neigh_vars[NEIGH_VAR_DELAY_PROBE_TIME].data = &p->delay_probe_time; + t->neigh_vars[NEIGH_VAR_GC_STALETIME].data = &p->gc_staletime; + t->neigh_vars[NEIGH_VAR_QUEUE_LEN].data = &p->queue_len_bytes; + t->neigh_vars[NEIGH_VAR_QUEUE_LEN_BYTES].data = &p->queue_len_bytes; + t->neigh_vars[NEIGH_VAR_PROXY_QLEN].data = &p->proxy_qlen; + t->neigh_vars[NEIGH_VAR_ANYCAST_DELAY].data = &p->anycast_delay; + t->neigh_vars[NEIGH_VAR_PROXY_DELAY].data = &p->proxy_delay; + t->neigh_vars[NEIGH_VAR_LOCKTIME].data = &p->locktime; + t->neigh_vars[NEIGH_VAR_RETRANS_TIME_MS].data = &p->retrans_time; + t->neigh_vars[NEIGH_VAR_BASE_REACHABLE_TIME_MS].data = &p->base_reachable_time; if (dev) { dev_name_source = dev->name; /* Terminate the table early */ - memset(&t->neigh_vars[14], 0, sizeof(t->neigh_vars[14])); + memset(&t->neigh_vars[NEIGH_VAR_GC_INTERVAL], 0, + sizeof(t->neigh_vars[NEIGH_VAR_GC_INTERVAL])); } else { dev_name_source = neigh_path[NEIGH_CTL_PATH_DEV].procname; - t->neigh_vars[14].data = (int *)(p + 1); - t->neigh_vars[15].data = (int *)(p + 1) + 1; - t->neigh_vars[16].data = (int *)(p + 1) + 2; - t->neigh_vars[17].data = (int *)(p + 1) + 3; + t->neigh_vars[NEIGH_VAR_GC_INTERVAL].data = (int *)(p + 1); + t->neigh_vars[NEIGH_VAR_GC_THRESH1].data = (int *)(p + 1) + 1; + t->neigh_vars[NEIGH_VAR_GC_THRESH2].data = (int *)(p + 1) + 2; + t->neigh_vars[NEIGH_VAR_GC_THRESH3].data = (int *)(p + 1) + 3; } if (handler) { /* RetransTime */ - t->neigh_vars[3].proc_handler = handler; - t->neigh_vars[3].extra1 = dev; + t->neigh_vars[NEIGH_VAR_RETRANS_TIME].proc_handler = handler; + t->neigh_vars[NEIGH_VAR_RETRANS_TIME].extra1 = dev; /* ReachableTime */ - t->neigh_vars[4].proc_handler = handler; - t->neigh_vars[4].extra1 = dev; + t->neigh_vars[NEIGH_VAR_BASE_REACHABLE_TIME].proc_handler = handler; + t->neigh_vars[NEIGH_VAR_BASE_REACHABLE_TIME].extra1 = dev; /* RetransTime (in milliseconds)*/ - t->neigh_vars[12].proc_handler = handler; - t->neigh_vars[12].extra1 = dev; + t->neigh_vars[NEIGH_VAR_RETRANS_TIME_MS].proc_handler = handler; + t->neigh_vars[NEIGH_VAR_RETRANS_TIME_MS].extra1 = dev; /* ReachableTime (in milliseconds) */ - t->neigh_vars[13].proc_handler = handler; - t->neigh_vars[13].extra1 = dev; + t->neigh_vars[NEIGH_VAR_BASE_REACHABLE_TIME_MS].proc_handler = handler; + t->neigh_vars[NEIGH_VAR_BASE_REACHABLE_TIME_MS].extra1 = dev; } t->dev_name = kstrdup(dev_name_source, GFP_KERNEL); diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index c71c434..db6c2f8 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -606,9 +606,12 @@ static ssize_t store_rps_map(struct netdev_rx_queue *queue, rcu_assign_pointer(queue->rps_map, map); spin_unlock(&rps_map_lock); - if (old_map) + if (map) + jump_label_inc(&rps_needed); + if (old_map) { kfree_rcu(old_map, rcu); - + jump_label_dec(&rps_needed); + } free_cpumask_var(mask); return len; } @@ -780,7 +783,7 @@ net_rx_queue_update_kobjects(struct net_device *net, int old_num, int new_num) #endif } -#ifdef CONFIG_XPS +#ifdef CONFIG_SYSFS /* * netdev_queue sysfs structures and functions. */ @@ -826,6 +829,23 @@ static const struct sysfs_ops netdev_queue_sysfs_ops = { .store = netdev_queue_attr_store, }; +static ssize_t show_trans_timeout(struct netdev_queue *queue, + struct netdev_queue_attribute *attribute, + char *buf) +{ + unsigned long trans_timeout; + + spin_lock_irq(&queue->_xmit_lock); + trans_timeout = queue->trans_timeout; + spin_unlock_irq(&queue->_xmit_lock); + + return sprintf(buf, "%lu", trans_timeout); +} + +static struct netdev_queue_attribute queue_trans_timeout = + __ATTR(tx_timeout, S_IRUGO, show_trans_timeout, NULL); + +#ifdef CONFIG_XPS static inline unsigned int get_netdev_queue_index(struct netdev_queue *queue) { struct net_device *dev = queue->dev; @@ -901,7 +921,7 @@ static ssize_t store_xps_map(struct netdev_queue *queue, struct xps_map *map, *new_map; struct xps_dev_maps *dev_maps, *new_dev_maps; int nonempty = 0; - int numa_node = -2; + int numa_node_id = -2; if (!capable(CAP_NET_ADMIN)) return -EPERM; @@ -944,10 +964,10 @@ static ssize_t store_xps_map(struct netdev_queue *queue, need_set = cpumask_test_cpu(cpu, mask) && cpu_online(cpu); #ifdef CONFIG_NUMA if (need_set) { - if (numa_node == -2) - numa_node = cpu_to_node(cpu); - else if (numa_node != cpu_to_node(cpu)) - numa_node = -1; + if (numa_node_id == -2) + numa_node_id = cpu_to_node(cpu); + else if (numa_node_id != cpu_to_node(cpu)) + numa_node_id = -1; } #endif if (need_set && pos >= map_len) { @@ -997,7 +1017,7 @@ static ssize_t store_xps_map(struct netdev_queue *queue, if (dev_maps) kfree_rcu(dev_maps, rcu); - netdev_queue_numa_node_write(queue, (numa_node >= 0) ? numa_node : + netdev_queue_numa_node_write(queue, (numa_node_id >= 0) ? numa_node_id : NUMA_NO_NODE); mutex_unlock(&xps_map_mutex); @@ -1020,12 +1040,17 @@ error: static struct netdev_queue_attribute xps_cpus_attribute = __ATTR(xps_cpus, S_IRUGO | S_IWUSR, show_xps_map, store_xps_map); +#endif /* CONFIG_XPS */ static struct attribute *netdev_queue_default_attrs[] = { + &queue_trans_timeout.attr, +#ifdef CONFIG_XPS &xps_cpus_attribute.attr, +#endif NULL }; +#ifdef CONFIG_XPS static void netdev_queue_release(struct kobject *kobj) { struct netdev_queue *queue = to_netdev_queue(kobj); @@ -1076,10 +1101,13 @@ static void netdev_queue_release(struct kobject *kobj) memset(kobj, 0, sizeof(*kobj)); dev_put(queue->dev); } +#endif /* CONFIG_XPS */ static struct kobj_type netdev_queue_ktype = { .sysfs_ops = &netdev_queue_sysfs_ops, +#ifdef CONFIG_XPS .release = netdev_queue_release, +#endif .default_attrs = netdev_queue_default_attrs, }; @@ -1102,12 +1130,12 @@ static int netdev_queue_add_kobject(struct net_device *net, int index) return error; } -#endif /* CONFIG_XPS */ +#endif /* CONFIG_SYSFS */ int netdev_queue_update_kobjects(struct net_device *net, int old_num, int new_num) { -#ifdef CONFIG_XPS +#ifdef CONFIG_SYSFS int i; int error = 0; @@ -1125,14 +1153,14 @@ netdev_queue_update_kobjects(struct net_device *net, int old_num, int new_num) return error; #else return 0; -#endif +#endif /* CONFIG_SYSFS */ } static int register_queue_kobjects(struct net_device *net) { int error = 0, txq = 0, rxq = 0, real_rx = 0, real_tx = 0; -#if defined(CONFIG_RPS) || defined(CONFIG_XPS) +#ifdef CONFIG_SYSFS net->queues_kset = kset_create_and_add("queues", NULL, &net->dev.kobj); if (!net->queues_kset) @@ -1173,7 +1201,7 @@ static void remove_queue_kobjects(struct net_device *net) net_rx_queue_update_kobjects(net, real_rx, 0); netdev_queue_update_kobjects(net, real_tx, 0); -#if defined(CONFIG_RPS) || defined(CONFIG_XPS) +#ifdef CONFIG_SYSFS kset_unregister(net->queues_kset); #endif } diff --git a/net/core/netpoll.c b/net/core/netpoll.c index cf64c1f..1a7d8e2 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -422,6 +422,7 @@ static void arp_reply(struct sk_buff *skb) struct sk_buff *send_skb; struct netpoll *np, *tmp; unsigned long flags; + int hlen, tlen; int hits = 0; if (list_empty(&npinfo->rx_np)) @@ -479,8 +480,9 @@ static void arp_reply(struct sk_buff *skb) if (tip != np->local_ip) continue; - send_skb = find_skb(np, size + LL_ALLOCATED_SPACE(np->dev), - LL_RESERVED_SPACE(np->dev)); + hlen = LL_RESERVED_SPACE(np->dev); + tlen = np->dev->needed_tailroom; + send_skb = find_skb(np, size + hlen + tlen, hlen); if (!send_skb) continue; diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c new file mode 100644 index 0000000..3a9fd48 --- /dev/null +++ b/net/core/netprio_cgroup.c @@ -0,0 +1,344 @@ +/* + * net/core/netprio_cgroup.c Priority Control Group + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + * Authors: Neil Horman <nhorman@tuxdriver.com> + */ + +#include <linux/module.h> +#include <linux/slab.h> +#include <linux/types.h> +#include <linux/string.h> +#include <linux/errno.h> +#include <linux/skbuff.h> +#include <linux/cgroup.h> +#include <linux/rcupdate.h> +#include <linux/atomic.h> +#include <net/rtnetlink.h> +#include <net/pkt_cls.h> +#include <net/sock.h> +#include <net/netprio_cgroup.h> + +static struct cgroup_subsys_state *cgrp_create(struct cgroup_subsys *ss, + struct cgroup *cgrp); +static void cgrp_destroy(struct cgroup_subsys *ss, struct cgroup *cgrp); +static int cgrp_populate(struct cgroup_subsys *ss, struct cgroup *cgrp); + +struct cgroup_subsys net_prio_subsys = { + .name = "net_prio", + .create = cgrp_create, + .destroy = cgrp_destroy, + .populate = cgrp_populate, +#ifdef CONFIG_NETPRIO_CGROUP + .subsys_id = net_prio_subsys_id, +#endif + .module = THIS_MODULE +}; + +#define PRIOIDX_SZ 128 + +static unsigned long prioidx_map[PRIOIDX_SZ]; +static DEFINE_SPINLOCK(prioidx_map_lock); +static atomic_t max_prioidx = ATOMIC_INIT(0); + +static inline struct cgroup_netprio_state *cgrp_netprio_state(struct cgroup *cgrp) +{ + return container_of(cgroup_subsys_state(cgrp, net_prio_subsys_id), + struct cgroup_netprio_state, css); +} + +static int get_prioidx(u32 *prio) +{ + unsigned long flags; + u32 prioidx; + + spin_lock_irqsave(&prioidx_map_lock, flags); + prioidx = find_first_zero_bit(prioidx_map, sizeof(unsigned long) * PRIOIDX_SZ); + set_bit(prioidx, prioidx_map); + spin_unlock_irqrestore(&prioidx_map_lock, flags); + if (prioidx == sizeof(unsigned long) * PRIOIDX_SZ) + return -ENOSPC; + + atomic_set(&max_prioidx, prioidx); + *prio = prioidx; + return 0; +} + +static void put_prioidx(u32 idx) +{ + unsigned long flags; + + spin_lock_irqsave(&prioidx_map_lock, flags); + clear_bit(idx, prioidx_map); + spin_unlock_irqrestore(&prioidx_map_lock, flags); +} + +static void extend_netdev_table(struct net_device *dev, u32 new_len) +{ + size_t new_size = sizeof(struct netprio_map) + + ((sizeof(u32) * new_len)); + struct netprio_map *new_priomap = kzalloc(new_size, GFP_KERNEL); + struct netprio_map *old_priomap; + int i; + + old_priomap = rtnl_dereference(dev->priomap); + + if (!new_priomap) { + printk(KERN_WARNING "Unable to alloc new priomap!\n"); + return; + } + + for (i = 0; + old_priomap && (i < old_priomap->priomap_len); + i++) + new_priomap->priomap[i] = old_priomap->priomap[i]; + + new_priomap->priomap_len = new_len; + + rcu_assign_pointer(dev->priomap, new_priomap); + if (old_priomap) + kfree_rcu(old_priomap, rcu); +} + +static void update_netdev_tables(void) +{ + struct net_device *dev; + u32 max_len = atomic_read(&max_prioidx); + struct netprio_map *map; + + rtnl_lock(); + for_each_netdev(&init_net, dev) { + map = rtnl_dereference(dev->priomap); + if ((!map) || + (map->priomap_len < max_len)) + extend_netdev_table(dev, max_len); + } + rtnl_unlock(); +} + +static struct cgroup_subsys_state *cgrp_create(struct cgroup_subsys *ss, + struct cgroup *cgrp) +{ + struct cgroup_netprio_state *cs; + int ret; + + cs = kzalloc(sizeof(*cs), GFP_KERNEL); + if (!cs) + return ERR_PTR(-ENOMEM); + + if (cgrp->parent && cgrp_netprio_state(cgrp->parent)->prioidx) { + kfree(cs); + return ERR_PTR(-EINVAL); + } + + ret = get_prioidx(&cs->prioidx); + if (ret != 0) { + printk(KERN_WARNING "No space in priority index array\n"); + kfree(cs); + return ERR_PTR(ret); + } + + return &cs->css; +} + +static void cgrp_destroy(struct cgroup_subsys *ss, struct cgroup *cgrp) +{ + struct cgroup_netprio_state *cs; + struct net_device *dev; + struct netprio_map *map; + + cs = cgrp_netprio_state(cgrp); + rtnl_lock(); + for_each_netdev(&init_net, dev) { + map = rtnl_dereference(dev->priomap); + if (map) + map->priomap[cs->prioidx] = 0; + } + rtnl_unlock(); + put_prioidx(cs->prioidx); + kfree(cs); +} + +static u64 read_prioidx(struct cgroup *cgrp, struct cftype *cft) +{ + return (u64)cgrp_netprio_state(cgrp)->prioidx; +} + +static int read_priomap(struct cgroup *cont, struct cftype *cft, + struct cgroup_map_cb *cb) +{ + struct net_device *dev; + u32 prioidx = cgrp_netprio_state(cont)->prioidx; + u32 priority; + struct netprio_map *map; + + rcu_read_lock(); + for_each_netdev_rcu(&init_net, dev) { + map = rcu_dereference(dev->priomap); + priority = map ? map->priomap[prioidx] : 0; + cb->fill(cb, dev->name, priority); + } + rcu_read_unlock(); + return 0; +} + +static int write_priomap(struct cgroup *cgrp, struct cftype *cft, + const char *buffer) +{ + char *devname = kstrdup(buffer, GFP_KERNEL); + int ret = -EINVAL; + u32 prioidx = cgrp_netprio_state(cgrp)->prioidx; + unsigned long priority; + char *priostr; + struct net_device *dev; + struct netprio_map *map; + + if (!devname) + return -ENOMEM; + + /* + * Minimally sized valid priomap string + */ + if (strlen(devname) < 3) + goto out_free_devname; + + priostr = strstr(devname, " "); + if (!priostr) + goto out_free_devname; + + /* + *Separate the devname from the associated priority + *and advance the priostr poitner to the priority value + */ + *priostr = '\0'; + priostr++; + + /* + * If the priostr points to NULL, we're at the end of the passed + * in string, and its not a valid write + */ + if (*priostr == '\0') + goto out_free_devname; + + ret = kstrtoul(priostr, 10, &priority); + if (ret < 0) + goto out_free_devname; + + ret = -ENODEV; + + dev = dev_get_by_name(&init_net, devname); + if (!dev) + goto out_free_devname; + + update_netdev_tables(); + ret = 0; + rcu_read_lock(); + map = rcu_dereference(dev->priomap); + if (map) + map->priomap[prioidx] = priority; + rcu_read_unlock(); + dev_put(dev); + +out_free_devname: + kfree(devname); + return ret; +} + +static struct cftype ss_files[] = { + { + .name = "prioidx", + .read_u64 = read_prioidx, + }, + { + .name = "ifpriomap", + .read_map = read_priomap, + .write_string = write_priomap, + }, +}; + +static int cgrp_populate(struct cgroup_subsys *ss, struct cgroup *cgrp) +{ + return cgroup_add_files(cgrp, ss, ss_files, ARRAY_SIZE(ss_files)); +} + +static int netprio_device_event(struct notifier_block *unused, + unsigned long event, void *ptr) +{ + struct net_device *dev = ptr; + struct netprio_map *old; + u32 max_len = atomic_read(&max_prioidx); + + /* + * Note this is called with rtnl_lock held so we have update side + * protection on our rcu assignments + */ + + switch (event) { + + case NETDEV_REGISTER: + if (max_len) + extend_netdev_table(dev, max_len); + break; + case NETDEV_UNREGISTER: + old = rtnl_dereference(dev->priomap); + RCU_INIT_POINTER(dev->priomap, NULL); + if (old) + kfree_rcu(old, rcu); + break; + } + return NOTIFY_DONE; +} + +static struct notifier_block netprio_device_notifier = { + .notifier_call = netprio_device_event +}; + +static int __init init_cgroup_netprio(void) +{ + int ret; + + ret = cgroup_load_subsys(&net_prio_subsys); + if (ret) + goto out; +#ifndef CONFIG_NETPRIO_CGROUP + smp_wmb(); + net_prio_subsys_id = net_prio_subsys.subsys_id; +#endif + + register_netdevice_notifier(&netprio_device_notifier); + +out: + return ret; +} + +static void __exit exit_cgroup_netprio(void) +{ + struct netprio_map *old; + struct net_device *dev; + + unregister_netdevice_notifier(&netprio_device_notifier); + + cgroup_unload_subsys(&net_prio_subsys); + +#ifndef CONFIG_NETPRIO_CGROUP + net_prio_subsys_id = -1; + synchronize_rcu(); +#endif + + rtnl_lock(); + for_each_netdev(&init_net, dev) { + old = rtnl_dereference(dev->priomap); + RCU_INIT_POINTER(dev->priomap, NULL); + if (old) + kfree_rcu(old, rcu); + } + rtnl_unlock(); +} + +module_init(init_cgroup_netprio); +module_exit(exit_cgroup_netprio); +MODULE_LICENSE("GPL v2"); diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 0001c24..aa53a35 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -1304,7 +1304,7 @@ static ssize_t pktgen_if_write(struct file *file, scan_ip6(buf, pkt_dev->in6_daddr.s6_addr); snprintf(buf, sizeof(buf), "%pI6c", &pkt_dev->in6_daddr); - ipv6_addr_copy(&pkt_dev->cur_in6_daddr, &pkt_dev->in6_daddr); + pkt_dev->cur_in6_daddr = pkt_dev->in6_daddr; if (debug) printk(KERN_DEBUG "pktgen: dst6 set to: %s\n", buf); @@ -1327,8 +1327,7 @@ static ssize_t pktgen_if_write(struct file *file, scan_ip6(buf, pkt_dev->min_in6_daddr.s6_addr); snprintf(buf, sizeof(buf), "%pI6c", &pkt_dev->min_in6_daddr); - ipv6_addr_copy(&pkt_dev->cur_in6_daddr, - &pkt_dev->min_in6_daddr); + pkt_dev->cur_in6_daddr = pkt_dev->min_in6_daddr; if (debug) printk(KERN_DEBUG "pktgen: dst6_min set to: %s\n", buf); @@ -1371,7 +1370,7 @@ static ssize_t pktgen_if_write(struct file *file, scan_ip6(buf, pkt_dev->in6_saddr.s6_addr); snprintf(buf, sizeof(buf), "%pI6c", &pkt_dev->in6_saddr); - ipv6_addr_copy(&pkt_dev->cur_in6_saddr, &pkt_dev->in6_saddr); + pkt_dev->cur_in6_saddr = pkt_dev->in6_saddr; if (debug) printk(KERN_DEBUG "pktgen: src6 set to: %s\n", buf); @@ -2079,9 +2078,7 @@ static void pktgen_setup_inject(struct pktgen_dev *pkt_dev) ifp = ifp->if_next) { if (ifp->scope == IFA_LINK && !(ifp->flags & IFA_F_TENTATIVE)) { - ipv6_addr_copy(&pkt_dev-> - cur_in6_saddr, - &ifp->addr); + pkt_dev->cur_in6_saddr = ifp->addr; err = 0; break; } @@ -2958,8 +2955,8 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev, iph->payload_len = htons(sizeof(struct udphdr) + datalen); iph->nexthdr = IPPROTO_UDP; - ipv6_addr_copy(&iph->daddr, &pkt_dev->cur_in6_daddr); - ipv6_addr_copy(&iph->saddr, &pkt_dev->cur_in6_saddr); + iph->daddr = pkt_dev->cur_in6_daddr; + iph->saddr = pkt_dev->cur_in6_saddr; skb->mac_header = (skb->network_header - ETH_HLEN - pkt_dev->pkt_overhead); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 06438f9..678ae4e 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -245,6 +245,55 @@ nodata: EXPORT_SYMBOL(__alloc_skb); /** + * build_skb - build a network buffer + * @data: data buffer provided by caller + * + * Allocate a new &sk_buff. Caller provides space holding head and + * skb_shared_info. @data must have been allocated by kmalloc() + * The return is the new skb buffer. + * On a failure the return is %NULL, and @data is not freed. + * Notes : + * Before IO, driver allocates only data buffer where NIC put incoming frame + * Driver should add room at head (NET_SKB_PAD) and + * MUST add room at tail (SKB_DATA_ALIGN(skb_shared_info)) + * After IO, driver calls build_skb(), to allocate sk_buff and populate it + * before giving packet to stack. + * RX rings only contains data buffers, not full skbs. + */ +struct sk_buff *build_skb(void *data) +{ + struct skb_shared_info *shinfo; + struct sk_buff *skb; + unsigned int size; + + skb = kmem_cache_alloc(skbuff_head_cache, GFP_ATOMIC); + if (!skb) + return NULL; + + size = ksize(data) - SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); + + memset(skb, 0, offsetof(struct sk_buff, tail)); + skb->truesize = SKB_TRUESIZE(size); + atomic_set(&skb->users, 1); + skb->head = data; + skb->data = data; + skb_reset_tail_pointer(skb); + skb->end = skb->tail + size; +#ifdef NET_SKBUFF_DATA_USES_OFFSET + skb->mac_header = ~0U; +#endif + + /* make sure we initialize shinfo sequentially */ + shinfo = skb_shinfo(skb); + memset(shinfo, 0, offsetof(struct skb_shared_info, dataref)); + atomic_set(&shinfo->dataref, 1); + kmemcheck_annotate_variable(shinfo->destructor_arg); + + return skb; +} +EXPORT_SYMBOL(build_skb); + +/** * __netdev_alloc_skb - allocate an skbuff for rx on a specific device * @dev: network device to receive on * @length: length to allocate @@ -2230,7 +2279,7 @@ static int skb_prepare_for_shift(struct sk_buff *skb) * @shiftlen: shift up to this many bytes * * Attempts to shift up to shiftlen worth of bytes, which may be less than - * the length of the skb, from tgt to skb. Returns number bytes shifted. + * the length of the skb, from skb to tgt. Returns number bytes shifted. * It's up to caller to free skb if everything was shifted. * * If @tgt runs out of frags, the whole operation is aborted. @@ -2621,7 +2670,7 @@ EXPORT_SYMBOL_GPL(skb_pull_rcsum); * a pointer to the first in a list of new skbs for the segments. * In case of error it returns ERR_PTR(err). */ -struct sk_buff *skb_segment(struct sk_buff *skb, u32 features) +struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features) { struct sk_buff *segs = NULL; struct sk_buff *tail = NULL; diff --git a/net/core/sock.c b/net/core/sock.c index cbdf51c..1606913 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -125,6 +125,7 @@ #include <net/xfrm.h> #include <linux/ipsec.h> #include <net/cls_cgroup.h> +#include <net/netprio_cgroup.h> #include <linux/filter.h> @@ -221,10 +222,16 @@ __u32 sysctl_rmem_default __read_mostly = SK_RMEM_MAX; int sysctl_optmem_max __read_mostly = sizeof(unsigned long)*(2*UIO_MAXIOV+512); EXPORT_SYMBOL(sysctl_optmem_max); -#if defined(CONFIG_CGROUPS) && !defined(CONFIG_NET_CLS_CGROUP) +#if defined(CONFIG_CGROUPS) +#if !defined(CONFIG_NET_CLS_CGROUP) int net_cls_subsys_id = -1; EXPORT_SYMBOL_GPL(net_cls_subsys_id); #endif +#if !defined(CONFIG_NETPRIO_CGROUP) +int net_prio_subsys_id = -1; +EXPORT_SYMBOL_GPL(net_prio_subsys_id); +#endif +#endif static int sock_set_timeout(long *timeo_p, char __user *optval, int optlen) { @@ -1120,6 +1127,18 @@ void sock_update_classid(struct sock *sk) sk->sk_classid = classid; } EXPORT_SYMBOL(sock_update_classid); + +void sock_update_netprioidx(struct sock *sk) +{ + struct cgroup_netprio_state *state; + if (in_interrupt()) + return; + rcu_read_lock(); + state = task_netprio_state(current); + sk->sk_cgrp_prioidx = state ? state->prioidx : 0; + rcu_read_unlock(); +} +EXPORT_SYMBOL_GPL(sock_update_netprioidx); #endif /** @@ -1147,6 +1166,7 @@ struct sock *sk_alloc(struct net *net, int family, gfp_t priority, atomic_set(&sk->sk_wmem_alloc, 1); sock_update_classid(sk); + sock_update_netprioidx(sk); } return sk; @@ -1213,7 +1233,14 @@ void sk_release_kernel(struct sock *sk) } EXPORT_SYMBOL(sk_release_kernel); -struct sock *sk_clone(const struct sock *sk, const gfp_t priority) +/** + * sk_clone_lock - clone a socket, and lock its clone + * @sk: the socket to clone + * @priority: for allocation (%GFP_KERNEL, %GFP_ATOMIC, etc) + * + * Caller must unlock socket even in error path (bh_unlock_sock(newsk)) + */ +struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) { struct sock *newsk; @@ -1306,7 +1333,7 @@ struct sock *sk_clone(const struct sock *sk, const gfp_t priority) out: return newsk; } -EXPORT_SYMBOL_GPL(sk_clone); +EXPORT_SYMBOL_GPL(sk_clone_lock); void sk_setup_caps(struct sock *sk, struct dst_entry *dst) { diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index 77a65f0..d05559d 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -68,8 +68,13 @@ static int rps_sock_flow_sysctl(ctl_table *table, int write, if (sock_table != orig_sock_table) { rcu_assign_pointer(rps_sock_flow_table, sock_table); - synchronize_rcu(); - vfree(orig_sock_table); + if (sock_table) + jump_label_inc(&rps_needed); + if (orig_sock_table) { + jump_label_dec(&rps_needed); + synchronize_rcu(); + vfree(orig_sock_table); + } } } |