diff options
Diffstat (limited to 'include')
99 files changed, 3234 insertions, 353 deletions
diff --git a/include/linux/audit.h b/include/linux/audit.h index 359df0487690..9d339eb27881 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -103,6 +103,8 @@ #define AUDIT_BPRM_FCAPS 1321 /* Information about fcaps increasing perms */ #define AUDIT_CAPSET 1322 /* Record showing argument to sys_capset */ #define AUDIT_MMAP 1323 /* Record showing descriptor and flags in mmap */ +#define AUDIT_NETFILTER_PKT 1324 /* Packets traversing netfilter chains */ +#define AUDIT_NETFILTER_CFG 1325 /* Netfilter chain modifications */ #define AUDIT_AVC 1400 /* SE Linux avc denial or grant */ #define AUDIT_SELINUX_ERR 1401 /* Internal SE Linux Errors */ diff --git a/include/linux/cpu_rmap.h b/include/linux/cpu_rmap.h new file mode 100644 index 000000000000..473771a528c0 --- /dev/null +++ b/include/linux/cpu_rmap.h @@ -0,0 +1,73 @@ +/* + * cpu_rmap.c: CPU affinity reverse-map support + * Copyright 2011 Solarflare Communications Inc. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published + * by the Free Software Foundation, incorporated herein by reference. + */ + +#include <linux/cpumask.h> +#include <linux/gfp.h> +#include <linux/slab.h> + +/** + * struct cpu_rmap - CPU affinity reverse-map + * @size: Number of objects to be reverse-mapped + * @used: Number of objects added + * @obj: Pointer to array of object pointers + * @near: For each CPU, the index and distance to the nearest object, + * based on affinity masks + */ +struct cpu_rmap { + u16 size, used; + void **obj; + struct { + u16 index; + u16 dist; + } near[0]; +}; +#define CPU_RMAP_DIST_INF 0xffff + +extern struct cpu_rmap *alloc_cpu_rmap(unsigned int size, gfp_t flags); + +/** + * free_cpu_rmap - free CPU affinity reverse-map + * @rmap: Reverse-map allocated with alloc_cpu_rmap(), or %NULL + */ +static inline void free_cpu_rmap(struct cpu_rmap *rmap) +{ + kfree(rmap); +} + +extern int cpu_rmap_add(struct cpu_rmap *rmap, void *obj); +extern int cpu_rmap_update(struct cpu_rmap *rmap, u16 index, + const struct cpumask *affinity); + +static inline u16 cpu_rmap_lookup_index(struct cpu_rmap *rmap, unsigned int cpu) +{ + return rmap->near[cpu].index; +} + +static inline void *cpu_rmap_lookup_obj(struct cpu_rmap *rmap, unsigned int cpu) +{ + return rmap->obj[rmap->near[cpu].index]; +} + +#ifdef CONFIG_GENERIC_HARDIRQS + +/** + * alloc_irq_cpu_rmap - allocate CPU affinity reverse-map for IRQs + * @size: Number of objects to be mapped + * + * Must be called in process context. + */ +static inline struct cpu_rmap *alloc_irq_cpu_rmap(unsigned int size) +{ + return alloc_cpu_rmap(size, GFP_KERNEL); +} +extern void free_irq_cpu_rmap(struct cpu_rmap *rmap); + +extern int irq_cpu_rmap_add(struct cpu_rmap *rmap, int irq); + +#endif diff --git a/include/linux/dccp.h b/include/linux/dccp.h index 010e2d87ed75..d638e85dc501 100644 --- a/include/linux/dccp.h +++ b/include/linux/dccp.h @@ -279,8 +279,6 @@ enum dccp_state { DCCP_MAX_STATES }; -#define DCCP_STATE_MASK 0x1f - enum { DCCPF_OPEN = TCPF_ESTABLISHED, DCCPF_REQUESTING = TCPF_SYN_SENT, diff --git a/include/linux/if_link.h b/include/linux/if_link.h index 6485d2a89bec..f4a2e6b1b864 100644 --- a/include/linux/if_link.h +++ b/include/linux/if_link.h @@ -135,6 +135,7 @@ enum { IFLA_VF_PORTS, IFLA_PORT_SELF, IFLA_AF_SPEC, + IFLA_GROUP, /* Group the device belongs to */ __IFLA_MAX }; diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 55e0d4253e49..63c5ad78e37c 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -14,6 +14,8 @@ #include <linux/smp.h> #include <linux/percpu.h> #include <linux/hrtimer.h> +#include <linux/kref.h> +#include <linux/workqueue.h> #include <asm/atomic.h> #include <asm/ptrace.h> @@ -240,6 +242,35 @@ extern int irq_can_set_affinity(unsigned int irq); extern int irq_select_affinity(unsigned int irq); extern int irq_set_affinity_hint(unsigned int irq, const struct cpumask *m); + +/** + * struct irq_affinity_notify - context for notification of IRQ affinity changes + * @irq: Interrupt to which notification applies + * @kref: Reference count, for internal use + * @work: Work item, for internal use + * @notify: Function to be called on change. This will be + * called in process context. + * @release: Function to be called on release. This will be + * called in process context. Once registered, the + * structure must only be freed when this function is + * called or later. + */ +struct irq_affinity_notify { + unsigned int irq; + struct kref kref; + struct work_struct work; + void (*notify)(struct irq_affinity_notify *, const cpumask_t *mask); + void (*release)(struct kref *ref); +}; + +extern int +irq_set_affinity_notifier(unsigned int irq, struct irq_affinity_notify *notify); + +static inline void irq_run_affinity_notifiers(void) +{ + flush_scheduled_work(); +} + #else /* CONFIG_SMP */ static inline int irq_set_affinity(unsigned int irq, const struct cpumask *m) @@ -255,7 +286,7 @@ static inline int irq_can_set_affinity(unsigned int irq) static inline int irq_select_affinity(unsigned int irq) { return 0; } static inline int irq_set_affinity_hint(unsigned int irq, - const struct cpumask *m) + const struct cpumask *m) { return -EINVAL; } diff --git a/include/linux/ip_vs.h b/include/linux/ip_vs.h index 5f43a3b2e3ad..4deb3834d62c 100644 --- a/include/linux/ip_vs.h +++ b/include/linux/ip_vs.h @@ -89,6 +89,14 @@ #define IP_VS_CONN_F_TEMPLATE 0x1000 /* template, not connection */ #define IP_VS_CONN_F_ONE_PACKET 0x2000 /* forward only one packet */ +#define IP_VS_CONN_F_BACKUP_MASK (IP_VS_CONN_F_FWD_MASK | \ + IP_VS_CONN_F_NOOUTPUT | \ + IP_VS_CONN_F_INACTIVE | \ + IP_VS_CONN_F_SEQ_MASK | \ + IP_VS_CONN_F_NO_CPORT | \ + IP_VS_CONN_F_TEMPLATE \ + ) + /* Flags that are not sent to backup server start from bit 16 */ #define IP_VS_CONN_F_NFCT (1 << 16) /* use netfilter conntrack */ diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h index c1a95b7b58de..bfef56dadddb 100644 --- a/include/linux/irqdesc.h +++ b/include/linux/irqdesc.h @@ -8,6 +8,7 @@ * For now it's included from <linux/irq.h> */ +struct irq_affinity_notify; struct proc_dir_entry; struct timer_rand_state; /** @@ -24,6 +25,7 @@ struct timer_rand_state; * @last_unhandled: aging timer for unhandled count * @irqs_unhandled: stats field for spurious unhandled interrupts * @lock: locking for SMP + * @affinity_notify: context for notification of affinity changes * @pending_mask: pending rebalanced interrupts * @threads_active: number of irqaction threads currently running * @wait_for_threads: wait queue for sync_irq to wait for threaded handlers @@ -70,6 +72,7 @@ struct irq_desc { raw_spinlock_t lock; #ifdef CONFIG_SMP const struct cpumask *affinity_hint; + struct irq_affinity_notify *affinity_notify; #ifdef CONFIG_GENERIC_PENDING_IRQ cpumask_var_t pending_mask; #endif diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index d971346b0340..c7d707452228 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -75,6 +75,9 @@ struct wireless_dev; #define NET_RX_SUCCESS 0 /* keep 'em coming, baby */ #define NET_RX_DROP 1 /* packet dropped */ +/* Initial net device group. All devices belong to group 0 by default. */ +#define INIT_NETDEV_GROUP 0 + /* * Transmit return codes: transmit return codes originate from three different * namespaces: @@ -551,14 +554,16 @@ struct rps_map { #define RPS_MAP_SIZE(_num) (sizeof(struct rps_map) + (_num * sizeof(u16))) /* - * The rps_dev_flow structure contains the mapping of a flow to a CPU and the - * tail pointer for that CPU's input queue at the time of last enqueue. + * The rps_dev_flow structure contains the mapping of a flow to a CPU, the + * tail pointer for that CPU's input queue at the time of last enqueue, and + * a hardware filter index. */ struct rps_dev_flow { u16 cpu; - u16 fill; + u16 filter; unsigned int last_qtail; }; +#define RPS_NO_FILTER 0xffff /* * The rps_dev_flow_table structure contains a table of flow mappings. @@ -608,6 +613,11 @@ static inline void rps_reset_sock_flow(struct rps_sock_flow_table *table, extern struct rps_sock_flow_table __rcu *rps_sock_flow_table; +#ifdef CONFIG_RFS_ACCEL +extern bool rps_may_expire_flow(struct net_device *dev, u16 rxq_index, + u32 flow_id, u16 filter_id); +#endif + /* This structure contains an instance of an RX queue. */ struct netdev_rx_queue { struct rps_map __rcu *rps_map; @@ -643,6 +653,14 @@ struct xps_dev_maps { (nr_cpu_ids * sizeof(struct xps_map *))) #endif /* CONFIG_XPS */ +#define TC_MAX_QUEUE 16 +#define TC_BITMASK 15 +/* HW offloaded queuing disciplines txq count and offset maps */ +struct netdev_tc_txq { + u16 count; + u16 offset; +}; + /* * This structure defines the management hooks for network devices. * The following hooks can be defined; unless noted otherwise, they are @@ -753,6 +771,18 @@ struct xps_dev_maps { * int (*ndo_set_vf_port)(struct net_device *dev, int vf, * struct nlattr *port[]); * int (*ndo_get_vf_port)(struct net_device *dev, int vf, struct sk_buff *skb); + * int (*ndo_setup_tc)(struct net_device *dev, u8 tc) + * Called to setup 'tc' number of traffic classes in the net device. This + * is always called from the stack with the rtnl lock held and netif tx + * queues stopped. This allows the netdevice to perform queue management + * safely. + * + * RFS acceleration. + * int (*ndo_rx_flow_steer)(struct net_device *dev, const struct sk_buff *skb, + * u16 rxq_index, u32 flow_id); + * Set hardware filter for RFS. rxq_index is the target queue index; + * flow_id is a flow ID to be passed to rps_may_expire_flow() later. + * Return the filter ID on success, or a negative error code. */ #define HAVE_NET_DEVICE_OPS struct net_device_ops { @@ -811,6 +841,7 @@ struct net_device_ops { struct nlattr *port[]); int (*ndo_get_vf_port)(struct net_device *dev, int vf, struct sk_buff *skb); + int (*ndo_setup_tc)(struct net_device *dev, u8 tc); #if defined(CONFIG_FCOE) || defined(CONFIG_FCOE_MODULE) int (*ndo_fcoe_enable)(struct net_device *dev); int (*ndo_fcoe_disable)(struct net_device *dev); @@ -825,6 +856,12 @@ struct net_device_ops { int (*ndo_fcoe_get_wwn)(struct net_device *dev, u64 *wwn, int type); #endif +#ifdef CONFIG_RFS_ACCEL + int (*ndo_rx_flow_steer)(struct net_device *dev, + const struct sk_buff *skb, + u16 rxq_index, + u32 flow_id); +#endif }; /* @@ -877,7 +914,11 @@ struct net_device { struct list_head unreg_list; /* Net device features */ - unsigned long features; + u32 features; + + /* VLAN feature mask */ + u32 vlan_features; + #define NETIF_F_SG 1 /* Scatter/gather IO. */ #define NETIF_F_IP_CSUM 2 /* Can checksum TCP/UDP over IPv4. */ #define NETIF_F_NO_CSUM 4 /* Does not require checksum. F.e. loopack. */ @@ -1039,6 +1080,13 @@ struct net_device { /* Number of RX queues currently active in device */ unsigned int real_num_rx_queues; + +#ifdef CONFIG_RFS_ACCEL + /* CPU reverse-mapping for RX completion interrupts, indexed + * by RX queue number. Assigned by driver. This must only be + * set if the ndo_rx_flow_steer operation is defined. */ + struct cpu_rmap *rx_cpu_rmap; +#endif #endif rx_handler_func_t __rcu *rx_handler; @@ -1132,9 +1180,6 @@ struct net_device { /* rtnetlink link ops */ const struct rtnl_link_ops *rtnl_link_ops; - /* VLAN feature mask */ - unsigned long vlan_features; - /* for setting kernel sock attribute on TCP connection setup */ #define GSO_MAX_SIZE 65536 unsigned int gso_max_size; @@ -1143,6 +1188,9 @@ struct net_device { /* Data Center Bridging netlink ops */ const struct dcbnl_rtnl_ops *dcbnl_ops; #endif + u8 num_tc; + struct netdev_tc_txq tc_to_txq[TC_MAX_QUEUE]; + u8 prio_tc_map[TC_BITMASK + 1]; #if defined(CONFIG_FCOE) || defined(CONFIG_FCOE_MODULE) /* max exchange id for FCoE LRO by ddp */ @@ -1153,12 +1201,66 @@ struct net_device { /* phy device may attach itself for hardware timestamping */ struct phy_device *phydev; + + /* group the device belongs to */ + int group; }; #define to_net_dev(d) container_of(d, struct net_device, dev) #define NETDEV_ALIGN 32 static inline +int netdev_get_prio_tc_map(const struct net_device *dev, u32 prio) +{ + return dev->prio_tc_map[prio & TC_BITMASK]; +} + +static inline +int netdev_set_prio_tc_map(struct net_device *dev, u8 prio, u8 tc) +{ + if (tc >= dev->num_tc) + return -EINVAL; + + dev->prio_tc_map[prio & TC_BITMASK] = tc & TC_BITMASK; + return 0; +} + +static inline +void netdev_reset_tc(struct net_device *dev) +{ + dev->num_tc = 0; + memset(dev->tc_to_txq, 0, sizeof(dev->tc_to_txq)); + memset(dev->prio_tc_map, 0, sizeof(dev->prio_tc_map)); +} + +static inline +int netdev_set_tc_queue(struct net_device *dev, u8 tc, u16 count, u16 offset) +{ + if (tc >= dev->num_tc) + return -EINVAL; + + dev->tc_to_txq[tc].count = count; + dev->tc_to_txq[tc].offset = offset; + return 0; +} + +static inline +int netdev_set_num_tc(struct net_device *dev, u8 num_tc) +{ + if (num_tc > TC_MAX_QUEUE) + return -EINVAL; + + dev->num_tc = num_tc; + return 0; +} + +static inline +int netdev_get_num_tc(struct net_device *dev) +{ + return dev->num_tc; +} + +static inline struct netdev_queue *netdev_get_tx_queue(const struct net_device *dev, unsigned int index) { @@ -1300,7 +1402,7 @@ struct packet_type { struct packet_type *, struct net_device *); struct sk_buff *(*gso_segment)(struct sk_buff *skb, - int features); + u32 features); int (*gso_send_check)(struct sk_buff *skb); struct sk_buff **(*gro_receive)(struct sk_buff **head, struct sk_buff *skb); @@ -1345,7 +1447,7 @@ static inline struct net_device *next_net_device_rcu(struct net_device *dev) struct net *net; net = dev_net(dev); - lh = rcu_dereference(dev->dev_list.next); + lh = rcu_dereference(list_next_rcu(&dev->dev_list)); return lh == &net->dev_base_head ? NULL : net_device_entry(lh); } @@ -1355,6 +1457,13 @@ static inline struct net_device *first_net_device(struct net *net) net_device_entry(net->dev_base_head.next); } +static inline struct net_device *first_net_device_rcu(struct net *net) +{ + struct list_head *lh = rcu_dereference(list_next_rcu(&net->dev_base_head)); + + return lh == &net->dev_base_head ? NULL : net_device_entry(lh); +} + extern int netdev_boot_setup_check(struct net_device *dev); extern unsigned long netdev_boot_base(const char *prefix, int unit); extern struct net_device *dev_getbyhwaddr_rcu(struct net *net, unsigned short type, @@ -1844,6 +1953,7 @@ extern int dev_set_alias(struct net_device *, const char *, size_t); extern int dev_change_net_namespace(struct net_device *, struct net *, const char *); extern int dev_set_mtu(struct net_device *, int); +extern void dev_set_group(struct net_device *, int); extern int dev_set_mac_address(struct net_device *, struct sockaddr *); extern int dev_hard_start_xmit(struct sk_buff *skb, @@ -2268,7 +2378,7 @@ extern int netdev_tstamp_prequeue; extern int weight_p; extern int netdev_set_master(struct net_device *dev, struct net_device *master); extern int skb_checksum_help(struct sk_buff *skb); -extern struct sk_buff *skb_gso_segment(struct sk_buff *skb, int features); +extern struct sk_buff *skb_gso_segment(struct sk_buff *skb, u32 features); #ifdef CONFIG_BUG extern void netdev_rx_csum_fault(struct net_device *dev); #else @@ -2295,22 +2405,21 @@ extern char *netdev_drivername(const struct net_device *dev, char *buffer, int l extern void linkwatch_run_queue(void); -unsigned long netdev_increment_features(unsigned long all, unsigned long one, - unsigned long mask); -unsigned long netdev_fix_features(unsigned long features, const char *name); +u32 netdev_increment_features(u32 all, u32 one, u32 mask); +u32 netdev_fix_features(struct net_device *dev, u32 features); void netif_stacked_transfer_operstate(const struct net_device *rootdev, struct net_device *dev); -int netif_skb_features(struct sk_buff *skb); +u32 netif_skb_features(struct sk_buff *skb); -static inline int net_gso_ok(int features, int gso_type) +static inline int net_gso_ok(u32 features, int gso_type) { int feature = gso_type << NETIF_F_GSO_SHIFT; return (features & feature) == feature; } -static inline int skb_gso_ok(struct sk_buff *skb, int features) +static inline int skb_gso_ok(struct sk_buff *skb, u32 features) { return net_gso_ok(features, skb_shinfo(skb)->gso_type) && (!skb_has_frag_list(skb) || (features & NETIF_F_FRAGLIST)); diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 1893837b3966..eeec00abb664 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -24,16 +24,20 @@ #define NF_MAX_VERDICT NF_STOP /* we overload the higher bits for encoding auxiliary data such as the queue - * number. Not nice, but better than additional function arguments. */ -#define NF_VERDICT_MASK 0x0000ffff -#define NF_VERDICT_BITS 16 + * number or errno values. Not nice, but better than additional function + * arguments. */ +#define NF_VERDICT_MASK 0x000000ff + +/* extra verdict flags have mask 0x0000ff00 */ +#define NF_VERDICT_FLAG_QUEUE_BYPASS 0x00008000 +/* queue number (NF_QUEUE) or errno (NF_DROP) */ #define NF_VERDICT_QMASK 0xffff0000 #define NF_VERDICT_QBITS 16 -#define NF_QUEUE_NR(x) ((((x) << NF_VERDICT_BITS) & NF_VERDICT_QMASK) | NF_QUEUE) +#define NF_QUEUE_NR(x) ((((x) << 16) & NF_VERDICT_QMASK) | NF_QUEUE) -#define NF_DROP_ERR(x) (((-x) << NF_VERDICT_BITS) | NF_DROP) +#define NF_DROP_ERR(x) (((-x) << 16) | NF_DROP) /* only for userspace compatibility */ #ifndef __KERNEL__ @@ -41,6 +45,9 @@ <= 0x2000 is used for protocol-flags. */ #define NFC_UNKNOWN 0x4000 #define NFC_ALTERED 0x8000 + +/* NF_VERDICT_BITS should be 8 now, but userspace might break if this changes */ +#define NF_VERDICT_BITS 16 #endif enum nf_inet_hooks { @@ -72,6 +79,10 @@ union nf_inet_addr { #ifdef __KERNEL__ #ifdef CONFIG_NETFILTER +static inline int NF_DROP_GETERR(int verdict) +{ + return -(verdict >> NF_VERDICT_QBITS); +} static inline int nf_inet_addr_cmp(const union nf_inet_addr *a1, const union nf_inet_addr *a2) @@ -267,7 +278,7 @@ struct nf_afinfo { int route_key_size; }; -extern const struct nf_afinfo *nf_afinfo[NFPROTO_NUMPROTO]; +extern const struct nf_afinfo __rcu *nf_afinfo[NFPROTO_NUMPROTO]; static inline const struct nf_afinfo *nf_get_afinfo(unsigned short family) { return rcu_dereference(nf_afinfo[family]); @@ -357,9 +368,9 @@ nf_nat_decode_session(struct sk_buff *skb, struct flowi *fl, u_int8_t family) #endif /*CONFIG_NETFILTER*/ #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) -extern void (*ip_ct_attach)(struct sk_buff *, struct sk_buff *); +extern void (*ip_ct_attach)(struct sk_buff *, struct sk_buff *) __rcu; extern void nf_ct_attach(struct sk_buff *, struct sk_buff *); -extern void (*nf_ct_destroy)(struct nf_conntrack *); +extern void (*nf_ct_destroy)(struct nf_conntrack *) __rcu; #else static inline void nf_ct_attach(struct sk_buff *new, struct sk_buff *skb) {} #endif diff --git a/include/linux/netfilter/Kbuild b/include/linux/netfilter/Kbuild index 9d40effe7ca7..15e83bf3dd58 100644 --- a/include/linux/netfilter/Kbuild +++ b/include/linux/netfilter/Kbuild @@ -1,3 +1,5 @@ +header-y += ipset/ + header-y += nf_conntrack_common.h header-y += nf_conntrack_ftp.h header-y += nf_conntrack_sctp.h @@ -9,6 +11,7 @@ header-y += nfnetlink_conntrack.h header-y += nfnetlink_log.h header-y += nfnetlink_queue.h header-y += x_tables.h +header-y += xt_AUDIT.h header-y += xt_CHECKSUM.h header-y += xt_CLASSIFY.h header-y += xt_CONNMARK.h @@ -34,6 +37,7 @@ header-y += xt_connmark.h header-y += xt_conntrack.h header-y += xt_cpu.h header-y += xt_dccp.h +header-y += xt_devgroup.h header-y += xt_dscp.h header-y += xt_esp.h header-y += xt_hashlimit.h @@ -54,7 +58,9 @@ header-y += xt_quota.h header-y += xt_rateest.h header-y += xt_realm.h header-y += xt_recent.h +header-y += xt_set.h header-y += xt_sctp.h +header-y += xt_socket.h header-y += xt_state.h header-y += xt_statistic.h header-y += xt_string.h diff --git a/include/linux/netfilter/ipset/Kbuild b/include/linux/netfilter/ipset/Kbuild new file mode 100644 index 000000000000..601fe71d34d5 --- /dev/null +++ b/include/linux/netfilter/ipset/Kbuild @@ -0,0 +1,4 @@ +header-y += ip_set.h +header-y += ip_set_bitmap.h +header-y += ip_set_hash.h +header-y += ip_set_list.h diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h new file mode 100644 index 000000000000..ec333d83f3b4 --- /dev/null +++ b/include/linux/netfilter/ipset/ip_set.h @@ -0,0 +1,452 @@ +#ifndef _IP_SET_H +#define _IP_SET_H + +/* Copyright (C) 2000-2002 Joakim Axelsson <gozem@linux.nu> + * Patrick Schaaf <bof@bof.de> + * Martin Josefsson <gandalf@wlug.westbo.se> + * Copyright (C) 2003-2011 Jozsef Kadlecsik <kadlec@blackhole.kfki.hu> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +/* The protocol version */ +#define IPSET_PROTOCOL 6 + +/* The max length of strings including NUL: set and type identifiers */ +#define IPSET_MAXNAMELEN 32 + +/* Message types and commands */ +enum ipset_cmd { + IPSET_CMD_NONE, + IPSET_CMD_PROTOCOL, /* 1: Return protocol version */ + IPSET_CMD_CREATE, /* 2: Create a new (empty) set */ + IPSET_CMD_DESTROY, /* 3: Destroy a (empty) set */ + IPSET_CMD_FLUSH, /* 4: Remove all elements from a set */ + IPSET_CMD_RENAME, /* 5: Rename a set */ + IPSET_CMD_SWAP, /* 6: Swap two sets */ + IPSET_CMD_LIST, /* 7: List sets */ + IPSET_CMD_SAVE, /* 8: Save sets */ + IPSET_CMD_ADD, /* 9: Add an element to a set */ + IPSET_CMD_DEL, /* 10: Delete an element from a set */ + IPSET_CMD_TEST, /* 11: Test an element in a set */ + IPSET_CMD_HEADER, /* 12: Get set header data only */ + IPSET_CMD_TYPE, /* 13: Get set type */ + IPSET_MSG_MAX, /* Netlink message commands */ + + /* Commands in userspace: */ + IPSET_CMD_RESTORE = IPSET_MSG_MAX, /* 14: Enter restore mode */ + IPSET_CMD_HELP, /* 15: Get help */ + IPSET_CMD_VERSION, /* 16: Get program version */ + IPSET_CMD_QUIT, /* 17: Quit from interactive mode */ + + IPSET_CMD_MAX, + + IPSET_CMD_COMMIT = IPSET_CMD_MAX, /* 18: Commit buffered commands */ +}; + +/* Attributes at command level */ +enum { + IPSET_ATTR_UNSPEC, + IPSET_ATTR_PROTOCOL, /* 1: Protocol version */ + IPSET_ATTR_SETNAME, /* 2: Name of the set */ + IPSET_ATTR_TYPENAME, /* 3: Typename */ + IPSET_ATTR_SETNAME2 = IPSET_ATTR_TYPENAME, /* Setname at rename/swap */ + IPSET_ATTR_REVISION, /* 4: Settype revision */ + IPSET_ATTR_FAMILY, /* 5: Settype family */ + IPSET_ATTR_FLAGS, /* 6: Flags at command level */ + IPSET_ATTR_DATA, /* 7: Nested attributes */ + IPSET_ATTR_ADT, /* 8: Multiple data containers */ + IPSET_ATTR_LINENO, /* 9: Restore lineno */ + IPSET_ATTR_PROTOCOL_MIN, /* 10: Minimal supported version number */ + IPSET_ATTR_REVISION_MIN = IPSET_ATTR_PROTOCOL_MIN, /* type rev min */ + __IPSET_ATTR_CMD_MAX, +}; +#define IPSET_ATTR_CMD_MAX (__IPSET_ATTR_CMD_MAX - 1) + +/* CADT specific attributes */ +enum { + IPSET_ATTR_IP = IPSET_ATTR_UNSPEC + 1, + IPSET_ATTR_IP_FROM = IPSET_ATTR_IP, + IPSET_ATTR_IP_TO, /* 2 */ + IPSET_ATTR_CIDR, /* 3 */ + IPSET_ATTR_PORT, /* 4 */ + IPSET_ATTR_PORT_FROM = IPSET_ATTR_PORT, + IPSET_ATTR_PORT_TO, /* 5 */ + IPSET_ATTR_TIMEOUT, /* 6 */ + IPSET_ATTR_PROTO, /* 7 */ + IPSET_ATTR_CADT_FLAGS, /* 8 */ + IPSET_ATTR_CADT_LINENO = IPSET_ATTR_LINENO, /* 9 */ + /* Reserve empty slots */ + IPSET_ATTR_CADT_MAX = 16, + /* Create-only specific attributes */ + IPSET_ATTR_GC, + IPSET_ATTR_HASHSIZE, + IPSET_ATTR_MAXELEM, + IPSET_ATTR_NETMASK, + IPSET_ATTR_PROBES, + IPSET_ATTR_RESIZE, + IPSET_ATTR_SIZE, + /* Kernel-only */ + IPSET_ATTR_ELEMENTS, + IPSET_ATTR_REFERENCES, + IPSET_ATTR_MEMSIZE, + + __IPSET_ATTR_CREATE_MAX, +}; +#define IPSET_ATTR_CREATE_MAX (__IPSET_ATTR_CREATE_MAX - 1) + +/* ADT specific attributes */ +enum { + IPSET_ATTR_ETHER = IPSET_ATTR_CADT_MAX + 1, + IPSET_ATTR_NAME, + IPSET_ATTR_NAMEREF, + IPSET_ATTR_IP2, + IPSET_ATTR_CIDR2, + __IPSET_ATTR_ADT_MAX, +}; +#define IPSET_ATTR_ADT_MAX (__IPSET_ATTR_ADT_MAX - 1) + +/* IP specific attributes */ +enum { + IPSET_ATTR_IPADDR_IPV4 = IPSET_ATTR_UNSPEC + 1, + IPSET_ATTR_IPADDR_IPV6, + __IPSET_ATTR_IPADDR_MAX, +}; +#define IPSET_ATTR_IPADDR_MAX (__IPSET_ATTR_IPADDR_MAX - 1) + +/* Error codes */ +enum ipset_errno { + IPSET_ERR_PRIVATE = 4096, + IPSET_ERR_PROTOCOL, + IPSET_ERR_FIND_TYPE, + IPSET_ERR_MAX_SETS, + IPSET_ERR_BUSY, + IPSET_ERR_EXIST_SETNAME2, + IPSET_ERR_TYPE_MISMATCH, + IPSET_ERR_EXIST, + IPSET_ERR_INVALID_CIDR, + IPSET_ERR_INVALID_NETMASK, + IPSET_ERR_INVALID_FAMILY, + IPSET_ERR_TIMEOUT, + IPSET_ERR_REFERENCED, + IPSET_ERR_IPADDR_IPV4, + IPSET_ERR_IPADDR_IPV6, + + /* Type specific error codes */ + IPSET_ERR_TYPE_SPECIFIC = 4352, +}; + +/* Flags at command level */ +enum ipset_cmd_flags { + IPSET_FLAG_BIT_EXIST = 0, + IPSET_FLAG_EXIST = (1 << IPSET_FLAG_BIT_EXIST), +}; + +/* Flags at CADT attribute level */ +enum ipset_cadt_flags { + IPSET_FLAG_BIT_BEFORE = 0, + IPSET_FLAG_BEFORE = (1 << IPSET_FLAG_BIT_BEFORE), +}; + +/* Commands with settype-specific attributes */ +enum ipset_adt { + IPSET_ADD, + IPSET_DEL, + IPSET_TEST, + IPSET_ADT_MAX, + IPSET_CREATE = IPSET_ADT_MAX, + IPSET_CADT_MAX, +}; + +#ifdef __KERNEL__ +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/netlink.h> +#include <linux/netfilter.h> +#include <linux/vmalloc.h> +#include <net/netlink.h> + +/* Sets are identified by an index in kernel space. Tweak with ip_set_id_t + * and IPSET_INVALID_ID if you want to increase the max number of sets. + */ +typedef u16 ip_set_id_t; + +#define IPSET_INVALID_ID 65535 + +enum ip_set_dim { + IPSET_DIM_ZERO = 0, + IPSET_DIM_ONE, + IPSET_DIM_TWO, + IPSET_DIM_THREE, + /* Max dimension in elements. + * If changed, new revision of iptables match/target is required. + */ + IPSET_DIM_MAX = 6, +}; + +/* Option flags for kernel operations */ +enum ip_set_kopt { + IPSET_INV_MATCH = (1 << IPSET_DIM_ZERO), + IPSET_DIM_ONE_SRC = (1 << IPSET_DIM_ONE), + IPSET_DIM_TWO_SRC = (1 << IPSET_DIM_TWO), + IPSET_DIM_THREE_SRC = (1 << IPSET_DIM_THREE), +}; + +/* Set features */ +enum ip_set_feature { + IPSET_TYPE_IP_FLAG = 0, + IPSET_TYPE_IP = (1 << IPSET_TYPE_IP_FLAG), + IPSET_TYPE_PORT_FLAG = 1, + IPSET_TYPE_PORT = (1 << IPSET_TYPE_PORT_FLAG), + IPSET_TYPE_MAC_FLAG = 2, + IPSET_TYPE_MAC = (1 << IPSET_TYPE_MAC_FLAG), + IPSET_TYPE_IP2_FLAG = 3, + IPSET_TYPE_IP2 = (1 << IPSET_TYPE_IP2_FLAG), + IPSET_TYPE_NAME_FLAG = 4, + IPSET_TYPE_NAME = (1 << IPSET_TYPE_NAME_FLAG), + /* Strictly speaking not a feature, but a flag for dumping: + * this settype must be dumped last */ + IPSET_DUMP_LAST_FLAG = 7, + IPSET_DUMP_LAST = (1 << IPSET_DUMP_LAST_FLAG), +}; + +struct ip_set; + +typedef int (*ipset_adtfn)(struct ip_set *set, void *value, u32 timeout); + +/* Set type, variant-specific part */ +struct ip_set_type_variant { + /* Kernelspace: test/add/del entries + * returns negative error code, + * zero for no match/success to add/delete + * positive for matching element */ + int (*kadt)(struct ip_set *set, const struct sk_buff * skb, + enum ipset_adt adt, u8 pf, u8 dim, u8 flags); + + /* Userspace: test/add/del entries + * returns negative error code, + * zero for no match/success to add/delete + * positive for matching element */ + int (*uadt)(struct ip_set *set, struct nlattr *tb[], + enum ipset_adt adt, u32 *lineno, u32 flags); + + /* Low level add/del/test functions */ + ipset_adtfn adt[IPSET_ADT_MAX]; + + /* When adding entries and set is full, try to resize the set */ + int (*resize)(struct ip_set *set, bool retried); + /* Destroy the set */ + void (*destroy)(struct ip_set *set); + /* Flush the elements */ + void (*flush)(struct ip_set *set); + /* Expire entries before listing */ + void (*expire)(struct ip_set *set); + /* List set header data */ + int (*head)(struct ip_set *set, struct sk_buff *skb); + /* List elements */ + int (*list)(const struct ip_set *set, struct sk_buff *skb, + struct netlink_callback *cb); + + /* Return true if "b" set is the same as "a" + * according to the create set parameters */ + bool (*same_set)(const struct ip_set *a, const struct ip_set *b); +}; + +/* The core set type structure */ +struct ip_set_type { + struct list_head list; + + /* Typename */ + char name[IPSET_MAXNAMELEN]; + /* Protocol version */ + u8 protocol; + /* Set features to control swapping */ + u8 features; + /* Set type dimension */ + u8 dimension; + /* Supported family: may be AF_UNSPEC for both AF_INET/AF_INET6 */ + u8 family; + /* Type revision */ + u8 revision; + + /* Create set */ + int (*create)(struct ip_set *set, struct nlattr *tb[], u32 flags); + + /* Attribute policies */ + const struct nla_policy create_policy[IPSET_ATTR_CREATE_MAX + 1]; + const struct nla_policy adt_policy[IPSET_ATTR_ADT_MAX + 1]; + + /* Set this to THIS_MODULE if you are a module, otherwise NULL */ + struct module *me; +}; + +/* register and unregister set type */ +extern int ip_set_type_register(struct ip_set_type *set_type); +extern void ip_set_type_unregister(struct ip_set_type *set_type); + +/* A generic IP set */ +struct ip_set { + /* The name of the set */ + char name[IPSET_MAXNAMELEN]; + /* Lock protecting the set data */ + rwlock_t lock; + /* References to the set */ + atomic_t ref; + /* The core set type */ + struct ip_set_type *type; + /* The type variant doing the real job */ + const struct ip_set_type_variant *variant; + /* The actual INET family of the set */ + u8 family; + /* The type specific data */ + void *data; +}; + +/* register and unregister set references */ +extern ip_set_id_t ip_set_get_byname(const char *name, struct ip_set **set); +extern void ip_set_put_byindex(ip_set_id_t index); +extern const char * ip_set_name_byindex(ip_set_id_t index); +extern ip_set_id_t ip_set_nfnl_get(const char *name); +extern ip_set_id_t ip_set_nfnl_get_byindex(ip_set_id_t index); +extern void ip_set_nfnl_put(ip_set_id_t index); + +/* API for iptables set match, and SET target */ +extern int ip_set_add(ip_set_id_t id, const struct sk_buff *skb, + u8 family, u8 dim, u8 flags); +extern int ip_set_del(ip_set_id_t id, const struct sk_buff *skb, + u8 family, u8 dim, u8 flags); +extern int ip_set_test(ip_set_id_t id, const struct sk_buff *skb, + u8 family, u8 dim, u8 flags); + +/* Utility functions */ +extern void * ip_set_alloc(size_t size); +extern void ip_set_free(void *members); +extern int ip_set_get_ipaddr4(struct nlattr *nla, __be32 *ipaddr); +extern int ip_set_get_ipaddr6(struct nlattr *nla, union nf_inet_addr *ipaddr); + +static inline int +ip_set_get_hostipaddr4(struct nlattr *nla, u32 *ipaddr) +{ + __be32 ip; + int ret = ip_set_get_ipaddr4(nla, &ip); + + if (ret) + return ret; + *ipaddr = ntohl(ip); + return 0; +} + +/* Ignore IPSET_ERR_EXIST errors if asked to do so? */ +static inline bool +ip_set_eexist(int ret, u32 flags) +{ + return ret == -IPSET_ERR_EXIST && (flags & IPSET_FLAG_EXIST); +} + +/* Check the NLA_F_NET_BYTEORDER flag */ +static inline bool +ip_set_attr_netorder(struct nlattr *tb[], int type) +{ + return tb[type] && (tb[type]->nla_type & NLA_F_NET_BYTEORDER); +} + +static inline bool +ip_set_optattr_netorder(struct nlattr *tb[], int type) +{ + return !tb[type] || (tb[type]->nla_type & NLA_F_NET_BYTEORDER); +} + +/* Useful converters */ +static inline u32 +ip_set_get_h32(const struct nlattr *attr) +{ + return ntohl(nla_get_be32(attr)); +} + +static inline u16 +ip_set_get_h16(const struct nlattr *attr) +{ + return ntohs(nla_get_be16(attr)); +} + +#define ipset_nest_start(skb, attr) nla_nest_start(skb, attr | NLA_F_NESTED) +#define ipset_nest_end(skb, start) nla_nest_end(skb, start) + +#define NLA_PUT_IPADDR4(skb, type, ipaddr) \ +do { \ + struct nlattr *__nested = ipset_nest_start(skb, type); \ + \ + if (!__nested) \ + goto nla_put_failure; \ + NLA_PUT_NET32(skb, IPSET_ATTR_IPADDR_IPV4, ipaddr); \ + ipset_nest_end(skb, __nested); \ +} while (0) + +#define NLA_PUT_IPADDR6(skb, type, ipaddrptr) \ +do { \ + struct nlattr *__nested = ipset_nest_start(skb, type); \ + \ + if (!__nested) \ + goto nla_put_failure; \ + NLA_PUT(skb, IPSET_ATTR_IPADDR_IPV6, \ + sizeof(struct in6_addr), ipaddrptr); \ + ipset_nest_end(skb, __nested); \ +} while (0) + +/* Get address from skbuff */ +static inline __be32 +ip4addr(const struct sk_buff *skb, bool src) +{ + return src ? ip_hdr(skb)->saddr : ip_hdr(skb)->daddr; +} + +static inline void +ip4addrptr(const struct sk_buff *skb, bool src, __be32 *addr) +{ + *addr = src ? ip_hdr(skb)->saddr : ip_hdr(skb)->daddr; +} + +static inline void +ip6addrptr(const struct sk_buff *skb, bool src, struct in6_addr *addr) +{ + memcpy(addr, src ? &ipv6_hdr(skb)->saddr : &ipv6_hdr(skb)->daddr, + sizeof(*addr)); +} + +/* Calculate the bytes required to store the inclusive range of a-b */ +static inline int +bitmap_bytes(u32 a, u32 b) +{ + return 4 * ((((b - a + 8) / 8) + 3) / 4); +} + +/* Interface to iptables/ip6tables */ + +#define SO_IP_SET 83 + +union ip_set_name_index { + char name[IPSET_MAXNAMELEN]; + ip_set_id_t index; +}; + +#define IP_SET_OP_GET_BYNAME 0x00000006 /* Get set index by name */ +struct ip_set_req_get_set { + unsigned op; + unsigned version; + union ip_set_name_index set; +}; + +#define IP_SET_OP_GET_BYINDEX 0x00000007 /* Get set name by index */ +/* Uses ip_set_req_get_set */ + +#define IP_SET_OP_VERSION 0x00000100 /* Ask kernel version */ +struct ip_set_req_version { + unsigned op; + unsigned version; +}; + +#endif /* __KERNEL__ */ + +#endif /*_IP_SET_H */ diff --git a/include/linux/netfilter/ipset/ip_set_ahash.h b/include/linux/netfilter/ipset/ip_set_ahash.h new file mode 100644 index 000000000000..ec9d9bea1e37 --- /dev/null +++ b/include/linux/netfilter/ipset/ip_set_ahash.h @@ -0,0 +1,1074 @@ +#ifndef _IP_SET_AHASH_H +#define _IP_SET_AHASH_H + +#include <linux/rcupdate.h> +#include <linux/jhash.h> +#include <linux/netfilter/ipset/ip_set_timeout.h> + +/* Hashing which uses arrays to resolve clashing. The hash table is resized + * (doubled) when searching becomes too long. + * Internally jhash is used with the assumption that the size of the + * stored data is a multiple of sizeof(u32). If storage supports timeout, + * the timeout field must be the last one in the data structure - that field + * is ignored when computing the hash key. + * + * Readers and resizing + * + * Resizing can be triggered by userspace command only, and those + * are serialized by the nfnl mutex. During resizing the set is + * read-locked, so the only possible concurrent operations are + * the kernel side readers. Those must be protected by proper RCU locking. + */ + +/* Number of elements to store in an initial array block */ +#define AHASH_INIT_SIZE 4 +/* Max number of elements to store in an array block */ +#define AHASH_MAX_SIZE (3*4) + +/* A hash bucket */ +struct hbucket { + void *value; /* the array of the values */ + u8 size; /* size of the array */ + u8 pos; /* position of the first free entry */ +}; + +/* The hash table: the table size stored here in order to make resizing easy */ +struct htable { + u8 htable_bits; /* size of hash table == 2^htable_bits */ + struct hbucket bucket[0]; /* hashtable buckets */ +}; + +#define hbucket(h, i) &((h)->bucket[i]) + +/* Book-keeping of the prefixes added to the set */ +struct ip_set_hash_nets { + u8 cidr; /* the different cidr values in the set */ + u32 nets; /* number of elements per cidr */ +}; + +/* The generic ip_set hash structure */ +struct ip_set_hash { + struct htable *table; /* the hash table */ + u32 maxelem; /* max elements in the hash */ + u32 elements; /* current element (vs timeout) */ + u32 initval; /* random jhash init value */ + u32 timeout; /* timeout value, if enabled */ + struct timer_list gc; /* garbage collection when timeout enabled */ +#ifdef IP_SET_HASH_WITH_NETMASK + u8 netmask; /* netmask value for subnets to store */ +#endif +#ifdef IP_SET_HASH_WITH_NETS + struct ip_set_hash_nets nets[0]; /* book-keeping of prefixes */ +#endif +}; + +/* Compute htable_bits from the user input parameter hashsize */ +static u8 +htable_bits(u32 hashsize) +{ + /* Assume that hashsize == 2^htable_bits */ + u8 bits = fls(hashsize - 1); + if (jhash_size(bits) != hashsize) + /* Round up to the first 2^n value */ + bits = fls(hashsize); + + return bits; +} + +#ifdef IP_SET_HASH_WITH_NETS + +#define SET_HOST_MASK(family) (family == AF_INET ? 32 : 128) + +/* Network cidr size book keeping when the hash stores different + * sized networks */ +static void +add_cidr(struct ip_set_hash *h, u8 cidr, u8 host_mask) +{ + u8 i; + + ++h->nets[cidr-1].nets; + + pr_debug("add_cidr added %u: %u\n", cidr, h->nets[cidr-1].nets); + + if (h->nets[cidr-1].nets > 1) + return; + + /* New cidr size */ + for (i = 0; i < host_mask && h->nets[i].cidr; i++) { + /* Add in increasing prefix order, so larger cidr first */ + if (h->nets[i].cidr < cidr) + swap(h->nets[i].cidr, cidr); + } + if (i < host_mask) + h->nets[i].cidr = cidr; +} + +static void +del_cidr(struct ip_set_hash *h, u8 cidr, u8 host_mask) +{ + u8 i; + + --h->nets[cidr-1].nets; + + pr_debug("del_cidr deleted %u: %u\n", cidr, h->nets[cidr-1].nets); + + if (h->nets[cidr-1].nets != 0) + return; + + /* All entries with this cidr size deleted, so cleanup h->cidr[] */ + for (i = 0; i < host_mask - 1 && h->nets[i].cidr; i++) { + if (h->nets[i].cidr == cidr) + h->nets[i].cidr = cidr = h->nets[i+1].cidr; + } + h->nets[i - 1].cidr = 0; +} +#endif + +/* Destroy the hashtable part of the set */ +static void +ahash_destroy(struct htable *t) +{ + struct hbucket *n; + u32 i; + + for (i = 0; i < jhash_size(t->htable_bits); i++) { + n = hbucket(t, i); + if (n->size) + /* FIXME: use slab cache */ + kfree(n->value); + } + + ip_set_free(t); +} + +/* Calculate the actual memory size of the set data */ +static size_t +ahash_memsize(const struct ip_set_hash *h, size_t dsize, u8 host_mask) +{ + u32 i; + struct htable *t = h->table; + size_t memsize = sizeof(*h) + + sizeof(*t) +#ifdef IP_SET_HASH_WITH_NETS + + sizeof(struct ip_set_hash_nets) * host_mask +#endif + + jhash_size(t->htable_bits) * sizeof(struct hbucket); + + for (i = 0; i < jhash_size(t->htable_bits); i++) + memsize += t->bucket[i].size * dsize; + + return memsize; +} + +/* Flush a hash type of set: destroy all elements */ +static void +ip_set_hash_flush(struct ip_set *set) +{ + struct ip_set_hash *h = set->data; + struct htable *t = h->table; + struct hbucket *n; + u32 i; + + for (i = 0; i < jhash_size(t->htable_bits); i++) { + n = hbucket(t, i); + if (n->size) { + n->size = n->pos = 0; + /* FIXME: use slab cache */ + kfree(n->value); + } + } +#ifdef IP_SET_HASH_WITH_NETS + memset(h->nets, 0, sizeof(struct ip_set_hash_nets) + * SET_HOST_MASK(set->family)); +#endif + h->elements = 0; +} + +/* Destroy a hash type of set */ +static void +ip_set_hash_destroy(struct ip_set *set) +{ + struct ip_set_hash *h = set->data; + + if (with_timeout(h->timeout)) + del_timer_sync(&h->gc); + + ahash_destroy(h->table); + kfree(h); + + set->data = NULL; +} + +#define HKEY(data, initval, htable_bits) \ +(jhash2((u32 *)(data), sizeof(struct type_pf_elem)/sizeof(u32), initval) \ + & jhash_mask(htable_bits)) + +#endif /* _IP_SET_AHASH_H */ + +#define CONCAT(a, b, c) a##b##c +#define TOKEN(a, b, c) CONCAT(a, b, c) + +/* Type/family dependent function prototypes */ + +#define type_pf_data_equal TOKEN(TYPE, PF, _data_equal) +#define type_pf_data_isnull TOKEN(TYPE, PF, _data_isnull) +#define type_pf_data_copy TOKEN(TYPE, PF, _data_copy) +#define type_pf_data_zero_out TOKEN(TYPE, PF, _data_zero_out) +#define type_pf_data_netmask TOKEN(TYPE, PF, _data_netmask) +#define type_pf_data_list TOKEN(TYPE, PF, _data_list) +#define type_pf_data_tlist TOKEN(TYPE, PF, _data_tlist) + +#define type_pf_elem TOKEN(TYPE, PF, _elem) +#define type_pf_telem TOKEN(TYPE, PF, _telem) +#define type_pf_data_timeout TOKEN(TYPE, PF, _data_timeout) +#define type_pf_data_expired TOKEN(TYPE, PF, _data_expired) +#define type_pf_data_timeout_set TOKEN(TYPE, PF, _data_timeout_set) + +#define type_pf_elem_add TOKEN(TYPE, PF, _elem_add) +#define type_pf_add TOKEN(TYPE, PF, _add) +#define type_pf_del TOKEN(TYPE, PF, _del) +#define type_pf_test_cidrs TOKEN(TYPE, PF, _test_cidrs) +#define type_pf_test TOKEN(TYPE, PF, _test) + +#define type_pf_elem_tadd TOKEN(TYPE, PF, _elem_tadd) +#define type_pf_del_telem TOKEN(TYPE, PF, _ahash_del_telem) +#define type_pf_expire TOKEN(TYPE, PF, _expire) +#define type_pf_tadd TOKEN(TYPE, PF, _tadd) +#define type_pf_tdel TOKEN(TYPE, PF, _tdel) +#define type_pf_ttest_cidrs TOKEN(TYPE, PF, _ahash_ttest_cidrs) +#define type_pf_ttest TOKEN(TYPE, PF, _ahash_ttest) + +#define type_pf_resize TOKEN(TYPE, PF, _resize) +#define type_pf_tresize TOKEN(TYPE, PF, _tresize) +#define type_pf_flush ip_set_hash_flush +#define type_pf_destroy ip_set_hash_destroy +#define type_pf_head TOKEN(TYPE, PF, _head) +#define type_pf_list TOKEN(TYPE, PF, _list) +#define type_pf_tlist TOKEN(TYPE, PF, _tlist) +#define type_pf_same_set TOKEN(TYPE, PF, _same_set) +#define type_pf_kadt TOKEN(TYPE, PF, _kadt) +#define type_pf_uadt TOKEN(TYPE, PF, _uadt) +#define type_pf_gc TOKEN(TYPE, PF, _gc) +#define type_pf_gc_init TOKEN(TYPE, PF, _gc_init) +#define type_pf_variant TOKEN(TYPE, PF, _variant) +#define type_pf_tvariant TOKEN(TYPE, PF, _tvariant) + +/* Flavour without timeout */ + +/* Get the ith element from the array block n */ +#define ahash_data(n, i) \ + ((struct type_pf_elem *)((n)->value) + (i)) + +/* Add an element to the hash table when resizing the set: + * we spare the maintenance of the internal counters. */ +static int +type_pf_elem_add(struct hbucket *n, const struct type_pf_elem *value) +{ + if (n->pos >= n->size) { + void *tmp; + + if (n->size >= AHASH_MAX_SIZE) + /* Trigger rehashing */ + return -EAGAIN; + + tmp = kzalloc((n->size + AHASH_INIT_SIZE) + * sizeof(struct type_pf_elem), + GFP_ATOMIC); + if (!tmp) + return -ENOMEM; + if (n->size) { + memcpy(tmp, n->value, + sizeof(struct type_pf_elem) * n->size); + kfree(n->value); + } + n->value = tmp; + n->size += AHASH_INIT_SIZE; + } + type_pf_data_copy(ahash_data(n, n->pos++), value); + return 0; +} + +/* Resize a hash: create a new hash table with doubling the hashsize + * and inserting the elements to it. Repeat until we succeed or + * fail due to memory pressures. */ +static int +type_pf_resize(struct ip_set *set, bool retried) +{ + struct ip_set_hash *h = set->data; + struct htable *t, *orig = h->table; + u8 htable_bits = orig->htable_bits; + const struct type_pf_elem *data; + struct hbucket *n, *m; + u32 i, j; + int ret; + +retry: + ret = 0; + htable_bits++; + pr_debug("attempt to resize set %s from %u to %u, t %p\n", + set->name, orig->htable_bits, htable_bits, orig); + if (!htable_bits) + /* In case we have plenty of memory :-) */ + return -IPSET_ERR_HASH_FULL; + t = ip_set_alloc(sizeof(*t) + + jhash_size(htable_bits) * sizeof(struct hbucket)); + if (!t) + return -ENOMEM; + t->htable_bits = htable_bits; + + read_lock_bh(&set->lock); + for (i = 0; i < jhash_size(orig->htable_bits); i++) { + n = hbucket(orig, i); + for (j = 0; j < n->pos; j++) { + data = ahash_data(n, j); + m = hbucket(t, HKEY(data, h->initval, htable_bits)); + ret = type_pf_elem_add(m, data); + if (ret < 0) { + read_unlock_bh(&set->lock); + ahash_destroy(t); + if (ret == -EAGAIN) + goto retry; + return ret; + } + } + } + + rcu_assign_pointer(h->table, t); + read_unlock_bh(&set->lock); + + /* Give time to other readers of the set */ + synchronize_rcu_bh(); + + pr_debug("set %s resized from %u (%p) to %u (%p)\n", set->name, + orig->htable_bits, orig, t->htable_bits, t); + ahash_destroy(orig); + + return 0; +} + +/* Add an element to a hash and update the internal counters when succeeded, + * otherwise report the proper error code. */ +static int +type_pf_add(struct ip_set *set, void *value, u32 timeout) +{ + struct ip_set_hash *h = set->data; + struct htable *t; + const struct type_pf_elem *d = value; + struct hbucket *n; + int i, ret = 0; + u32 key; + + if (h->elements >= h->maxelem) + return -IPSET_ERR_HASH_FULL; + + rcu_read_lock_bh(); + t = rcu_dereference_bh(h->table); + key = HKEY(value, h->initval, t->htable_bits); + n = hbucket(t, key); + for (i = 0; i < n->pos; i++) + if (type_pf_data_equal(ahash_data(n, i), d)) { + ret = -IPSET_ERR_EXIST; + goto out; + } + + ret = type_pf_elem_add(n, value); + if (ret != 0) + goto out; + +#ifdef IP_SET_HASH_WITH_NETS + add_cidr(h, d->cidr, HOST_MASK); +#endif + h->elements++; +out: + rcu_read_unlock_bh(); + return ret; +} + +/* Delete an element from the hash: swap it with the last element + * and free up space if possible. + */ +static int +type_pf_del(struct ip_set *set, void *value, u32 timeout) +{ + struct ip_set_hash *h = set->data; + struct htable *t = h->table; + const struct type_pf_elem *d = value; + struct hbucket *n; + int i; + struct type_pf_elem *data; + u32 key; + + key = HKEY(value, h->initval, t->htable_bits); + n = hbucket(t, key); + for (i = 0; i < n->pos; i++) { + data = ahash_data(n, i); + if (!type_pf_data_equal(data, d)) + continue; + if (i != n->pos - 1) + /* Not last one */ + type_pf_data_copy(data, ahash_data(n, n->pos - 1)); + + n->pos--; + h->elements--; +#ifdef IP_SET_HASH_WITH_NETS + del_cidr(h, d->cidr, HOST_MASK); +#endif + if (n->pos + AHASH_INIT_SIZE < n->size) { + void *tmp = kzalloc((n->size - AHASH_INIT_SIZE) + * sizeof(struct type_pf_elem), + GFP_ATOMIC); + if (!tmp) + return 0; + n->size -= AHASH_INIT_SIZE; + memcpy(tmp, n->value, + n->size * sizeof(struct type_pf_elem)); + kfree(n->value); + n->value = tmp; + } + return 0; + } + + return -IPSET_ERR_EXIST; +} + +#ifdef IP_SET_HASH_WITH_NETS + +/* Special test function which takes into account the different network + * sizes added to the set */ +static int +type_pf_test_cidrs(struct ip_set *set, struct type_pf_elem *d, u32 timeout) +{ + struct ip_set_hash *h = set->data; + struct htable *t = h->table; + struct hbucket *n; + const struct type_pf_elem *data; + int i, j = 0; + u32 key; + u8 host_mask = SET_HOST_MASK(set->family); + + pr_debug("test by nets\n"); + for (; j < host_mask && h->nets[j].cidr; j++) { + type_pf_data_netmask(d, h->nets[j].cidr); + key = HKEY(d, h->initval, t->htable_bits); + n = hbucket(t, key); + for (i = 0; i < n->pos; i++) { + data = ahash_data(n, i); + if (type_pf_data_equal(data, d)) + return 1; + } + } + return 0; +} +#endif + +/* Test whether the element is added to the set */ +static int +type_pf_test(struct ip_set *set, void *value, u32 timeout) +{ + struct ip_set_hash *h = set->data; + struct htable *t = h->table; + struct type_pf_elem *d = value; + struct hbucket *n; + const struct type_pf_elem *data; + int i; + u32 key; + +#ifdef IP_SET_HASH_WITH_NETS + /* If we test an IP address and not a network address, + * try all possible network sizes */ + if (d->cidr == SET_HOST_MASK(set->family)) + return type_pf_test_cidrs(set, d, timeout); +#endif + + key = HKEY(d, h->initval, t->htable_bits); + n = hbucket(t, key); + for (i = 0; i < n->pos; i++) { + data = ahash_data(n, i); + if (type_pf_data_equal(data, d)) + return 1; + } + return 0; +} + +/* Reply a HEADER request: fill out the header part of the set */ +static int +type_pf_head(struct ip_set *set, struct sk_buff *skb) +{ + const struct ip_set_hash *h = set->data; + struct nlattr *nested; + size_t memsize; + + read_lock_bh(&set->lock); + memsize = ahash_memsize(h, with_timeout(h->timeout) + ? sizeof(struct type_pf_telem) + : sizeof(struct type_pf_elem), + set->family == AF_INET ? 32 : 128); + read_unlock_bh(&set->lock); + + nested = ipset_nest_start(skb, IPSET_ATTR_DATA); + if (!nested) + goto nla_put_failure; + NLA_PUT_NET32(skb, IPSET_ATTR_HASHSIZE, + htonl(jhash_size(h->table->htable_bits))); + NLA_PUT_NET32(skb, IPSET_ATTR_MAXELEM, htonl(h->maxelem)); +#ifdef IP_SET_HASH_WITH_NETMASK + if (h->netmask != HOST_MASK) + NLA_PUT_U8(skb, IPSET_ATTR_NETMASK, h->netmask); +#endif + NLA_PUT_NET32(skb, IPSET_ATTR_REFERENCES, + htonl(atomic_read(&set->ref) - 1)); + NLA_PUT_NET32(skb, IPSET_ATTR_MEMSIZE, htonl(memsize)); + if (with_timeout(h->timeout)) + NLA_PUT_NET32(skb, IPSET_ATTR_TIMEOUT, htonl(h->timeout)); + ipset_nest_end(skb, nested); + + return 0; +nla_put_failure: + return -EMSGSIZE; +} + +/* Reply a LIST/SAVE request: dump the elements of the specified set */ +static int +type_pf_list(const struct ip_set *set, + struct sk_buff *skb, struct netlink_callback *cb) +{ + const struct ip_set_hash *h = set->data; + const struct htable *t = h->table; + struct nlattr *atd, *nested; + const struct hbucket *n; + const struct type_pf_elem *data; + u32 first = cb->args[2]; + /* We assume that one hash bucket fills into one page */ + void *incomplete; + int i; + + atd = ipset_nest_start(skb, IPSET_ATTR_ADT); + if (!atd) + return -EMSGSIZE; + pr_debug("list hash set %s\n", set->name); + for (; cb->args[2] < jhash_size(t->htable_bits); cb->args[2]++) { + incomplete = skb_tail_pointer(skb); + n = hbucket(t, cb->args[2]); + pr_debug("cb->args[2]: %lu, t %p n %p\n", cb->args[2], t, n); + for (i = 0; i < n->pos; i++) { + data = ahash_data(n, i); + pr_debug("list hash %lu hbucket %p i %u, data %p\n", + cb->args[2], n, i, data); + nested = ipset_nest_start(skb, IPSET_ATTR_DATA); + if (!nested) { + if (cb->args[2] == first) { + nla_nest_cancel(skb, atd); + return -EMSGSIZE; + } else + goto nla_put_failure; + } + if (type_pf_data_list(skb, data)) + goto nla_put_failure; + ipset_nest_end(skb, nested); + } + } + ipset_nest_end(skb, atd); + /* Set listing finished */ + cb->args[2] = 0; + + return 0; + +nla_put_failure: + nlmsg_trim(skb, incomplete); + ipset_nest_end(skb, atd); + if (unlikely(first == cb->args[2])) { + pr_warning("Can't list set %s: one bucket does not fit into " + "a message. Please report it!\n", set->name); + cb->args[2] = 0; + return -EMSGSIZE; + } + return 0; +} + +static int +type_pf_kadt(struct ip_set *set, const struct sk_buff * skb, + enum ipset_adt adt, u8 pf, u8 dim, u8 flags); +static int +type_pf_uadt(struct ip_set *set, struct nlattr *tb[], + enum ipset_adt adt, u32 *lineno, u32 flags); + +static const struct ip_set_type_variant type_pf_variant = { + .kadt = type_pf_kadt, + .uadt = type_pf_uadt, + .adt = { + [IPSET_ADD] = type_pf_add, + [IPSET_DEL] = type_pf_del, + [IPSET_TEST] = type_pf_test, + }, + .destroy = type_pf_destroy, + .flush = type_pf_flush, + .head = type_pf_head, + .list = type_pf_list, + .resize = type_pf_resize, + .same_set = type_pf_same_set, +}; + +/* Flavour with timeout support */ + +#define ahash_tdata(n, i) \ + (struct type_pf_elem *)((struct type_pf_telem *)((n)->value) + (i)) + +static inline u32 +type_pf_data_timeout(const struct type_pf_elem *data) +{ + const struct type_pf_telem *tdata = + (const struct type_pf_telem *) data; + + return tdata->timeout; +} + +static inline bool +type_pf_data_expired(const struct type_pf_elem *data) +{ + const struct type_pf_telem *tdata = + (const struct type_pf_telem *) data; + + return ip_set_timeout_expired(tdata->timeout); +} + +static inline void +type_pf_data_timeout_set(struct type_pf_elem *data, u32 timeout) +{ + struct type_pf_telem *tdata = (struct type_pf_telem *) data; + + tdata->timeout = ip_set_timeout_set(timeout); +} + +static int +type_pf_elem_tadd(struct hbucket *n, const struct type_pf_elem *value, + u32 timeout) +{ + struct type_pf_elem *data; + + if (n->pos >= n->size) { + void *tmp; + + if (n->size >= AHASH_MAX_SIZE) + /* Trigger rehashing */ + return -EAGAIN; + + tmp = kzalloc((n->size + AHASH_INIT_SIZE) + * sizeof(struct type_pf_telem), + GFP_ATOMIC); + if (!tmp) + return -ENOMEM; + if (n->size) { + memcpy(tmp, n->value, + sizeof(struct type_pf_telem) * n->size); + kfree(n->value); + } + n->value = tmp; + n->size += AHASH_INIT_SIZE; + } + data = ahash_tdata(n, n->pos++); + type_pf_data_copy(data, value); + type_pf_data_timeout_set(data, timeout); + return 0; +} + +/* Delete expired elements from the hashtable */ +static void +type_pf_expire(struct ip_set_hash *h) +{ + struct htable *t = h->table; + struct hbucket *n; + struct type_pf_elem *data; + u32 i; + int j; + + for (i = 0; i < jhash_size(t->htable_bits); i++) { + n = hbucket(t, i); + for (j = 0; j < n->pos; j++) { + data = ahash_tdata(n, j); + if (type_pf_data_expired(data)) { + pr_debug("expired %u/%u\n", i, j); +#ifdef IP_SET_HASH_WITH_NETS + del_cidr(h, data->cidr, HOST_MASK); +#endif + if (j != n->pos - 1) + /* Not last one */ + type_pf_data_copy(data, + ahash_tdata(n, n->pos - 1)); + n->pos--; + h->elements--; + } + } + if (n->pos + AHASH_INIT_SIZE < n->size) { + void *tmp = kzalloc((n->size - AHASH_INIT_SIZE) + * sizeof(struct type_pf_telem), + GFP_ATOMIC); + if (!tmp) + /* Still try to delete expired elements */ + continue; + n->size -= AHASH_INIT_SIZE; + memcpy(tmp, n->value, + n->size * sizeof(struct type_pf_telem)); + kfree(n->value); + n->value = tmp; + } + } +} + +static int +type_pf_tresize(struct ip_set *set, bool retried) +{ + struct ip_set_hash *h = set->data; + struct htable *t, *orig = h->table; + u8 htable_bits = orig->htable_bits; + const struct type_pf_elem *data; + struct hbucket *n, *m; + u32 i, j; + int ret; + + /* Try to cleanup once */ + if (!retried) { + i = h->elements; + write_lock_bh(&set->lock); + type_pf_expire(set->data); + write_unlock_bh(&set->lock); + if (h->elements < i) + return 0; + } + +retry: + ret = 0; + htable_bits++; + if (!htable_bits) + /* In case we have plenty of memory :-) */ + return -IPSET_ERR_HASH_FULL; + t = ip_set_alloc(sizeof(*t) + + jhash_size(htable_bits) * sizeof(struct hbucket)); + if (!t) + return -ENOMEM; + t->htable_bits = htable_bits; + + read_lock_bh(&set->lock); + for (i = 0; i < jhash_size(orig->htable_bits); i++) { + n = hbucket(orig, i); + for (j = 0; j < n->pos; j++) { + data = ahash_tdata(n, j); + m = hbucket(t, HKEY(data, h->initval, htable_bits)); + ret = type_pf_elem_tadd(m, data, + type_pf_data_timeout(data)); + if (ret < 0) { + read_unlock_bh(&set->lock); + ahash_destroy(t); + if (ret == -EAGAIN) + goto retry; + return ret; + } + } + } + + rcu_assign_pointer(h->table, t); + read_unlock_bh(&set->lock); + + /* Give time to other readers of the set */ + synchronize_rcu_bh(); + + ahash_destroy(orig); + + return 0; +} + +static int +type_pf_tadd(struct ip_set *set, void *value, u32 timeout) +{ + struct ip_set_hash *h = set->data; + struct htable *t = h->table; + const struct type_pf_elem *d = value; + struct hbucket *n; + struct type_pf_elem *data; + int ret = 0, i, j = AHASH_MAX_SIZE + 1; + u32 key; + + if (h->elements >= h->maxelem) + /* FIXME: when set is full, we slow down here */ + type_pf_expire(h); + if (h->elements >= h->maxelem) + return -IPSET_ERR_HASH_FULL; + + rcu_read_lock_bh(); + t = rcu_dereference_bh(h->table); + key = HKEY(d, h->initval, t->htable_bits); + n = hbucket(t, key); + for (i = 0; i < n->pos; i++) { + data = ahash_tdata(n, i); + if (type_pf_data_equal(data, d)) { + if (type_pf_data_expired(data)) + j = i; + else { + ret = -IPSET_ERR_EXIST; + goto out; + } + } else if (j == AHASH_MAX_SIZE + 1 && + type_pf_data_expired(data)) + j = i; + } + if (j != AHASH_MAX_SIZE + 1) { + data = ahash_tdata(n, j); +#ifdef IP_SET_HASH_WITH_NETS + del_cidr(h, data->cidr, HOST_MASK); + add_cidr(h, d->cidr, HOST_MASK); +#endif + type_pf_data_copy(data, d); + type_pf_data_timeout_set(data, timeout); + goto out; + } + ret = type_pf_elem_tadd(n, d, timeout); + if (ret != 0) + goto out; + +#ifdef IP_SET_HASH_WITH_NETS + add_cidr(h, d->cidr, HOST_MASK); +#endif + h->elements++; +out: + rcu_read_unlock_bh(); + return ret; +} + +static int +type_pf_tdel(struct ip_set *set, void *value, u32 timeout) +{ + struct ip_set_hash *h = set->data; + struct htable *t = h->table; + const struct type_pf_elem *d = value; + struct hbucket *n; + int i, ret = 0; + struct type_pf_elem *data; + u32 key; + + key = HKEY(value, h->initval, t->htable_bits); + n = hbucket(t, key); + for (i = 0; i < n->pos; i++) { + data = ahash_tdata(n, i); + if (!type_pf_data_equal(data, d)) + continue; + if (type_pf_data_expired(data)) + ret = -IPSET_ERR_EXIST; + if (i != n->pos - 1) + /* Not last one */ + type_pf_data_copy(data, ahash_tdata(n, n->pos - 1)); + + n->pos--; + h->elements--; +#ifdef IP_SET_HASH_WITH_NETS + del_cidr(h, d->cidr, HOST_MASK); +#endif + if (n->pos + AHASH_INIT_SIZE < n->size) { + void *tmp = kzalloc((n->size - AHASH_INIT_SIZE) + * sizeof(struct type_pf_telem), + GFP_ATOMIC); + if (!tmp) + return 0; + n->size -= AHASH_INIT_SIZE; + memcpy(tmp, n->value, + n->size * sizeof(struct type_pf_telem)); + kfree(n->value); + n->value = tmp; + } + return 0; + } + + return -IPSET_ERR_EXIST; +} + +#ifdef IP_SET_HASH_WITH_NETS +static int +type_pf_ttest_cidrs(struct ip_set *set, struct type_pf_elem *d, u32 timeout) +{ + struct ip_set_hash *h = set->data; + struct htable *t = h->table; + struct type_pf_elem *data; + struct hbucket *n; + int i, j = 0; + u32 key; + u8 host_mask = SET_HOST_MASK(set->family); + + for (; j < host_mask && h->nets[j].cidr; j++) { + type_pf_data_netmask(d, h->nets[j].cidr); + key = HKEY(d, h->initval, t->htable_bits); + n = hbucket(t, key); + for (i = 0; i < n->pos; i++) { + data = ahash_tdata(n, i); + if (type_pf_data_equal(data, d)) + return !type_pf_data_expired(data); + } + } + return 0; +} +#endif + +static int +type_pf_ttest(struct ip_set *set, void *value, u32 timeout) +{ + struct ip_set_hash *h = set->data; + struct htable *t = h->table; + struct type_pf_elem *data, *d = value; + struct hbucket *n; + int i; + u32 key; + +#ifdef IP_SET_HASH_WITH_NETS + if (d->cidr == SET_HOST_MASK(set->family)) + return type_pf_ttest_cidrs(set, d, timeout); +#endif + key = HKEY(d, h->initval, t->htable_bits); + n = hbucket(t, key); + for (i = 0; i < n->pos; i++) { + data = ahash_tdata(n, i); + if (type_pf_data_equal(data, d)) + return !type_pf_data_expired(data); + } + return 0; +} + +static int +type_pf_tlist(const struct ip_set *set, + struct sk_buff *skb, struct netlink_callback *cb) +{ + const struct ip_set_hash *h = set->data; + const struct htable *t = h->table; + struct nlattr *atd, *nested; + const struct hbucket *n; + const struct type_pf_elem *data; + u32 first = cb->args[2]; + /* We assume that one hash bucket fills into one page */ + void *incomplete; + int i; + + atd = ipset_nest_start(skb, IPSET_ATTR_ADT); + if (!atd) + return -EMSGSIZE; + for (; cb->args[2] < jhash_size(t->htable_bits); cb->args[2]++) { + incomplete = skb_tail_pointer(skb); + n = hbucket(t, cb->args[2]); + for (i = 0; i < n->pos; i++) { + data = ahash_tdata(n, i); + pr_debug("list %p %u\n", n, i); + if (type_pf_data_expired(data)) + continue; + pr_debug("do list %p %u\n", n, i); + nested = ipset_nest_start(skb, IPSET_ATTR_DATA); + if (!nested) { + if (cb->args[2] == first) { + nla_nest_cancel(skb, atd); + return -EMSGSIZE; + } else + goto nla_put_failure; + } + if (type_pf_data_tlist(skb, data)) + goto nla_put_failure; + ipset_nest_end(skb, nested); + } + } + ipset_nest_end(skb, atd); + /* Set listing finished */ + cb->args[2] = 0; + + return 0; + +nla_put_failure: + nlmsg_trim(skb, incomplete); + ipset_nest_end(skb, atd); + if (unlikely(first == cb->args[2])) { + pr_warning("Can't list set %s: one bucket does not fit into " + "a message. Please report it!\n", set->name); + cb->args[2] = 0; + return -EMSGSIZE; + } + return 0; +} + +static const struct ip_set_type_variant type_pf_tvariant = { + .kadt = type_pf_kadt, + .uadt = type_pf_uadt, + .adt = { + [IPSET_ADD] = type_pf_tadd, + [IPSET_DEL] = type_pf_tdel, + [IPSET_TEST] = type_pf_ttest, + }, + .destroy = type_pf_destroy, + .flush = type_pf_flush, + .head = type_pf_head, + .list = type_pf_tlist, + .resize = type_pf_tresize, + .same_set = type_pf_same_set, +}; + +static void +type_pf_gc(unsigned long ul_set) +{ + struct ip_set *set = (struct ip_set *) ul_set; + struct ip_set_hash *h = set->data; + + pr_debug("called\n"); + write_lock_bh(&set->lock); + type_pf_expire(h); + write_unlock_bh(&set->lock); + + h->gc.expires = jiffies + IPSET_GC_PERIOD(h->timeout) * HZ; + add_timer(&h->gc); +} + +static void +type_pf_gc_init(struct ip_set *set) +{ + struct ip_set_hash *h = set->data; + + init_timer(&h->gc); + h->gc.data = (unsigned long) set; + h->gc.function = type_pf_gc; + h->gc.expires = jiffies + IPSET_GC_PERIOD(h->timeout) * HZ; + add_timer(&h->gc); + pr_debug("gc initialized, run in every %u\n", + IPSET_GC_PERIOD(h->timeout)); +} + +#undef type_pf_data_equal +#undef type_pf_data_isnull +#undef type_pf_data_copy +#undef type_pf_data_zero_out +#undef type_pf_data_list +#undef type_pf_data_tlist + +#undef type_pf_elem +#undef type_pf_telem +#undef type_pf_data_timeout +#undef type_pf_data_expired +#undef type_pf_data_netmask +#undef type_pf_data_timeout_set + +#undef type_pf_elem_add +#undef type_pf_add +#undef type_pf_del +#undef type_pf_test_cidrs +#undef type_pf_test + +#undef type_pf_elem_tadd +#undef type_pf_expire +#undef type_pf_tadd +#undef type_pf_tdel +#undef type_pf_ttest_cidrs +#undef type_pf_ttest + +#undef type_pf_resize +#undef type_pf_tresize +#undef type_pf_flush +#undef type_pf_destroy +#undef type_pf_head +#undef type_pf_list +#undef type_pf_tlist +#undef type_pf_same_set +#undef type_pf_kadt +#undef type_pf_uadt +#undef type_pf_gc +#undef type_pf_gc_init +#undef type_pf_variant +#undef type_pf_tvariant diff --git a/include/linux/netfilter/ipset/ip_set_bitmap.h b/include/linux/netfilter/ipset/ip_set_bitmap.h new file mode 100644 index 000000000000..61a9e8746c83 --- /dev/null +++ b/include/linux/netfilter/ipset/ip_set_bitmap.h @@ -0,0 +1,31 @@ +#ifndef __IP_SET_BITMAP_H +#define __IP_SET_BITMAP_H + +/* Bitmap type specific error codes */ +enum { + /* The element is out of the range of the set */ + IPSET_ERR_BITMAP_RANGE = IPSET_ERR_TYPE_SPECIFIC, + /* The range exceeds the size limit of the set type */ + IPSET_ERR_BITMAP_RANGE_SIZE, +}; + +#ifdef __KERNEL__ +#define IPSET_BITMAP_MAX_RANGE 0x0000FFFF + +/* Common functions */ + +static inline u32 +range_to_mask(u32 from, u32 to, u8 *bits) +{ + u32 mask = 0xFFFFFFFE; + + *bits = 32; + while (--(*bits) > 0 && mask && (to & mask) != from) + mask <<= 1; + + return mask; +} + +#endif /* __KERNEL__ */ + +#endif /* __IP_SET_BITMAP_H */ diff --git a/include/linux/netfilter/ipset/ip_set_getport.h b/include/linux/netfilter/ipset/ip_set_getport.h new file mode 100644 index 000000000000..3882a81a3b3c --- /dev/null +++ b/include/linux/netfilter/ipset/ip_set_getport.h @@ -0,0 +1,21 @@ +#ifndef _IP_SET_GETPORT_H +#define _IP_SET_GETPORT_H + +extern bool ip_set_get_ip4_port(const struct sk_buff *skb, bool src, + __be16 *port, u8 *proto); + +#if defined(CONFIG_IP6_NF_IPTABLES) || defined(CONFIG_IP6_NF_IPTABLES_MODULE) +extern bool ip_set_get_ip6_port(const struct sk_buff *skb, bool src, + __be16 *port, u8 *proto); +#else +static inline bool ip_set_get_ip6_port(const struct sk_buff *skb, bool src, + __be16 *port, u8 *proto) +{ + return false; +} +#endif + +extern bool ip_set_get_ip_port(const struct sk_buff *skb, u8 pf, bool src, + __be16 *port); + +#endif /*_IP_SET_GETPORT_H*/ diff --git a/include/linux/netfilter/ipset/ip_set_hash.h b/include/linux/netfilter/ipset/ip_set_hash.h new file mode 100644 index 000000000000..b86f15c04524 --- /dev/null +++ b/include/linux/netfilter/ipset/ip_set_hash.h @@ -0,0 +1,26 @@ +#ifndef __IP_SET_HASH_H +#define __IP_SET_HASH_H + +/* Hash type specific error codes */ +enum { + /* Hash is full */ + IPSET_ERR_HASH_FULL = IPSET_ERR_TYPE_SPECIFIC, + /* Null-valued element */ + IPSET_ERR_HASH_ELEM, + /* Invalid protocol */ + IPSET_ERR_INVALID_PROTO, + /* Protocol missing but must be specified */ + IPSET_ERR_MISSING_PROTO, +}; + +#ifdef __KERNEL__ + +#define IPSET_DEFAULT_HASHSIZE 1024 +#define IPSET_MIMINAL_HASHSIZE 64 +#define IPSET_DEFAULT_MAXELEM 65536 +#define IPSET_DEFAULT_PROBES 4 +#define IPSET_DEFAULT_RESIZE 100 + +#endif /* __KERNEL__ */ + +#endif /* __IP_SET_HASH_H */ diff --git a/include/linux/netfilter/ipset/ip_set_list.h b/include/linux/netfilter/ipset/ip_set_list.h new file mode 100644 index 000000000000..40a63f302613 --- /dev/null +++ b/include/linux/netfilter/ipset/ip_set_list.h @@ -0,0 +1,27 @@ +#ifndef __IP_SET_LIST_H +#define __IP_SET_LIST_H + +/* List type specific error codes */ +enum { + /* Set name to be added/deleted/tested does not exist. */ + IPSET_ERR_NAME = IPSET_ERR_TYPE_SPECIFIC, + /* list:set type is not permitted to add */ + IPSET_ERR_LOOP, + /* Missing reference set */ + IPSET_ERR_BEFORE, + /* Reference set does not exist */ + IPSET_ERR_NAMEREF, + /* Set is full */ + IPSET_ERR_LIST_FULL, + /* Reference set is not added to the set */ + IPSET_ERR_REF_EXIST, +}; + +#ifdef __KERNEL__ + +#define IP_SET_LIST_DEFAULT_SIZE 8 +#define IP_SET_LIST_MIN_SIZE 4 + +#endif /* __KERNEL__ */ + +#endif /* __IP_SET_LIST_H */ diff --git a/include/linux/netfilter/ipset/ip_set_timeout.h b/include/linux/netfilter/ipset/ip_set_timeout.h new file mode 100644 index 000000000000..9f30c5f2ec1c --- /dev/null +++ b/include/linux/netfilter/ipset/ip_set_timeout.h @@ -0,0 +1,127 @@ +#ifndef _IP_SET_TIMEOUT_H +#define _IP_SET_TIMEOUT_H + +/* Copyright (C) 2003-2011 Jozsef Kadlecsik <kadlec@blackhole.kfki.hu> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifdef __KERNEL__ + +/* How often should the gc be run by default */ +#define IPSET_GC_TIME (3 * 60) + +/* Timeout period depending on the timeout value of the given set */ +#define IPSET_GC_PERIOD(timeout) \ + ((timeout/3) ? min_t(u32, (timeout)/3, IPSET_GC_TIME) : 1) + +/* Set is defined without timeout support: timeout value may be 0 */ +#define IPSET_NO_TIMEOUT UINT_MAX + +#define with_timeout(timeout) ((timeout) != IPSET_NO_TIMEOUT) + +static inline unsigned int +ip_set_timeout_uget(struct nlattr *tb) +{ + unsigned int timeout = ip_set_get_h32(tb); + + /* Userspace supplied TIMEOUT parameter: adjust crazy size */ + return timeout == IPSET_NO_TIMEOUT ? IPSET_NO_TIMEOUT - 1 : timeout; +} + +#ifdef IP_SET_BITMAP_TIMEOUT + +/* Bitmap specific timeout constants and macros for the entries */ + +/* Bitmap entry is unset */ +#define IPSET_ELEM_UNSET 0 +/* Bitmap entry is set with no timeout value */ +#define IPSET_ELEM_PERMANENT (UINT_MAX/2) + +static inline bool +ip_set_timeout_test(unsigned long timeout) +{ + return timeout != IPSET_ELEM_UNSET && + (timeout == IPSET_ELEM_PERMANENT || + time_after(timeout, jiffies)); +} + +static inline bool +ip_set_timeout_expired(unsigned long timeout) +{ + return timeout != IPSET_ELEM_UNSET && + timeout != IPSET_ELEM_PERMANENT && + time_before(timeout, jiffies); +} + +static inline unsigned long +ip_set_timeout_set(u32 timeout) +{ + unsigned long t; + + if (!timeout) + return IPSET_ELEM_PERMANENT; + + t = timeout * HZ + jiffies; + if (t == IPSET_ELEM_UNSET || t == IPSET_ELEM_PERMANENT) + /* Bingo! */ + t++; + + return t; +} + +static inline u32 +ip_set_timeout_get(unsigned long timeout) +{ + return timeout == IPSET_ELEM_PERMANENT ? 0 : (timeout - jiffies)/HZ; +} + +#else + +/* Hash specific timeout constants and macros for the entries */ + +/* Hash entry is set with no timeout value */ +#define IPSET_ELEM_PERMANENT 0 + +static inline bool +ip_set_timeout_test(unsigned long timeout) +{ + return timeout == IPSET_ELEM_PERMANENT || + time_after(timeout, jiffies); +} + +static inline bool +ip_set_timeout_expired(unsigned long timeout) +{ + return timeout != IPSET_ELEM_PERMANENT && + time_before(timeout, jiffies); +} + +static inline unsigned long +ip_set_timeout_set(u32 timeout) +{ + unsigned long t; + + if (!timeout) + return IPSET_ELEM_PERMANENT; + + t = timeout * HZ + jiffies; + if (t == IPSET_ELEM_PERMANENT) + /* Bingo! :-) */ + t++; + + return t; +} + +static inline u32 +ip_set_timeout_get(unsigned long timeout) +{ + return timeout == IPSET_ELEM_PERMANENT ? 0 : (timeout - jiffies)/HZ; +} +#endif /* ! IP_SET_BITMAP_TIMEOUT */ + +#endif /* __KERNEL__ */ + +#endif /* _IP_SET_TIMEOUT_H */ diff --git a/include/linux/netfilter/ipset/pfxlen.h b/include/linux/netfilter/ipset/pfxlen.h new file mode 100644 index 000000000000..0e1fb50da562 --- /dev/null +++ b/include/linux/netfilter/ipset/pfxlen.h @@ -0,0 +1,35 @@ +#ifndef _PFXLEN_H +#define _PFXLEN_H + +#include <asm/byteorder.h> +#include <linux/netfilter.h> + +/* Prefixlen maps, by Jan Engelhardt */ +extern const union nf_inet_addr ip_set_netmask_map[]; +extern const union nf_inet_addr ip_set_hostmask_map[]; + +static inline __be32 +ip_set_netmask(u8 pfxlen) +{ + return ip_set_netmask_map[pfxlen].ip; +} + +static inline const __be32 * +ip_set_netmask6(u8 pfxlen) +{ + return &ip_set_netmask_map[pfxlen].ip6[0]; +} + +static inline u32 +ip_set_hostmask(u8 pfxlen) +{ + return (__force u32) ip_set_hostmask_map[pfxlen].ip; +} + +static inline const __be32 * +ip_set_hostmask6(u8 pfxlen) +{ + return &ip_set_hostmask_map[pfxlen].ip6[0]; +} + +#endif /*_PFXLEN_H */ diff --git a/include/linux/netfilter/nf_conntrack_snmp.h b/include/linux/netfilter/nf_conntrack_snmp.h new file mode 100644 index 000000000000..064bc63a5346 --- /dev/null +++ b/include/linux/netfilter/nf_conntrack_snmp.h @@ -0,0 +1,9 @@ +#ifndef _NF_CONNTRACK_SNMP_H +#define _NF_CONNTRACK_SNMP_H + +extern int (*nf_nat_snmp_hook)(struct sk_buff *skb, + unsigned int protoff, + struct nf_conn *ct, + enum ip_conntrack_info ctinfo); + +#endif /* _NF_CONNTRACK_SNMP_H */ diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h index 361d6b5630ee..2b11fc1a86be 100644 --- a/include/linux/netfilter/nfnetlink.h +++ b/include/linux/netfilter/nfnetlink.h @@ -47,7 +47,8 @@ struct nfgenmsg { #define NFNL_SUBSYS_QUEUE 3 #define NFNL_SUBSYS_ULOG 4 #define NFNL_SUBSYS_OSF 5 -#define NFNL_SUBSYS_COUNT 6 +#define NFNL_SUBSYS_IPSET 6 +#define NFNL_SUBSYS_COUNT 7 #ifdef __KERNEL__ diff --git a/include/linux/netfilter/nfnetlink_conntrack.h b/include/linux/netfilter/nfnetlink_conntrack.h index 19711e3ffd42..debf1aefd753 100644 --- a/include/linux/netfilter/nfnetlink_conntrack.h +++ b/include/linux/netfilter/nfnetlink_conntrack.h @@ -42,6 +42,7 @@ enum ctattr_type { CTA_SECMARK, /* obsolete */ CTA_ZONE, CTA_SECCTX, + CTA_TIMESTAMP, __CTA_MAX }; #define CTA_MAX (__CTA_MAX - 1) @@ -127,6 +128,14 @@ enum ctattr_counters { }; #define CTA_COUNTERS_MAX (__CTA_COUNTERS_MAX - 1) +enum ctattr_tstamp { + CTA_TIMESTAMP_UNSPEC, + CTA_TIMESTAMP_START, + CTA_TIMESTAMP_STOP, + __CTA_TIMESTAMP_MAX +}; +#define CTA_TIMESTAMP_MAX (__CTA_TIMESTAMP_MAX - 1) + enum ctattr_nat { CTA_NAT_UNSPEC, CTA_NAT_MINIP, diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index 6712e713b299..37219525ff6f 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -611,8 +611,9 @@ struct _compat_xt_align { extern void xt_compat_lock(u_int8_t af); extern void xt_compat_unlock(u_int8_t af); -extern int xt_compat_add_offset(u_int8_t af, unsigned int offset, short delta); +extern int xt_compat_add_offset(u_int8_t af, unsigned int offset, int delta); extern void xt_compat_flush_offsets(u_int8_t af); +extern void xt_compat_init_offsets(u_int8_t af, unsigned int number); extern int xt_compat_calc_jump(u_int8_t af, unsigned int offset); extern int xt_compat_match_offset(const struct xt_match *match); diff --git a/include/linux/netfilter/xt_AUDIT.h b/include/linux/netfilter/xt_AUDIT.h new file mode 100644 index 000000000000..38751d2ea52b --- /dev/null +++ b/include/linux/netfilter/xt_AUDIT.h @@ -0,0 +1,30 @@ +/* + * Header file for iptables xt_AUDIT target + * + * (C) 2010-2011 Thomas Graf <tgraf@redhat.com> + * (C) 2010-2011 Red Hat, Inc. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef _XT_AUDIT_TARGET_H +#define _XT_AUDIT_TARGET_H + +#include <linux/types.h> + +enum { + XT_AUDIT_TYPE_ACCEPT = 0, + XT_AUDIT_TYPE_DROP, + XT_AUDIT_TYPE_REJECT, + __XT_AUDIT_TYPE_MAX, +}; + +#define XT_AUDIT_TYPE_MAX (__XT_AUDIT_TYPE_MAX - 1) + +struct xt_audit_info { + __u8 type; /* XT_AUDIT_TYPE_* */ +}; + +#endif /* _XT_AUDIT_TARGET_H */ diff --git a/include/linux/netfilter/xt_CT.h b/include/linux/netfilter/xt_CT.h index 1b564106891d..b56e76811c04 100644 --- a/include/linux/netfilter/xt_CT.h +++ b/include/linux/netfilter/xt_CT.h @@ -1,14 +1,16 @@ #ifndef _XT_CT_H #define _XT_CT_H +#include <linux/types.h> + #define XT_CT_NOTRACK 0x1 struct xt_ct_target_info { - u_int16_t flags; - u_int16_t zone; - u_int32_t ct_events; - u_int32_t exp_events; - char helper[16]; + __u16 flags; + __u16 zone; + __u32 ct_events; + __u32 exp_events; + char helper[16]; /* Used internally by the kernel */ struct nf_conn *ct __attribute__((aligned(8))); diff --git a/include/linux/netfilter/xt_NFQUEUE.h b/include/linux/netfilter/xt_NFQUEUE.h index 2584f4a777de..9eafdbbb401c 100644 --- a/include/linux/netfilter/xt_NFQUEUE.h +++ b/include/linux/netfilter/xt_NFQUEUE.h @@ -20,4 +20,10 @@ struct xt_NFQ_info_v1 { __u16 queues_total; }; +struct xt_NFQ_info_v2 { + __u16 queuenum; + __u16 queues_total; + __u16 bypass; +}; + #endif /* _XT_NFQ_TARGET_H */ diff --git a/include/linux/netfilter/xt_TCPOPTSTRIP.h b/include/linux/netfilter/xt_TCPOPTSTRIP.h index 2db543214ff5..7157318499c2 100644 --- a/include/linux/netfilter/xt_TCPOPTSTRIP.h +++ b/include/linux/netfilter/xt_TCPOPTSTRIP.h @@ -1,13 +1,15 @@ #ifndef _XT_TCPOPTSTRIP_H #define _XT_TCPOPTSTRIP_H +#include <linux/types.h> + #define tcpoptstrip_set_bit(bmap, idx) \ (bmap[(idx) >> 5] |= 1U << (idx & 31)) #define tcpoptstrip_test_bit(bmap, idx) \ (((1U << (idx & 31)) & bmap[(idx) >> 5]) != 0) struct xt_tcpoptstrip_target_info { - u_int32_t strip_bmap[8]; + __u32 strip_bmap[8]; }; #endif /* _XT_TCPOPTSTRIP_H */ diff --git a/include/linux/netfilter/xt_TPROXY.h b/include/linux/netfilter/xt_TPROXY.h index 3f3d69361289..902043c2073f 100644 --- a/include/linux/netfilter/xt_TPROXY.h +++ b/include/linux/netfilter/xt_TPROXY.h @@ -1,19 +1,21 @@ #ifndef _XT_TPROXY_H #define _XT_TPROXY_H +#include <linux/types.h> + /* TPROXY target is capable of marking the packet to perform * redirection. We can get rid of that whenever we get support for * mutliple targets in the same rule. */ struct xt_tproxy_target_info { - u_int32_t mark_mask; - u_int32_t mark_value; + __u32 mark_mask; + __u32 mark_value; __be32 laddr; __be16 lport; }; struct xt_tproxy_target_info_v1 { - u_int32_t mark_mask; - u_int32_t mark_value; + __u32 mark_mask; + __u32 mark_value; union nf_inet_addr laddr; __be16 lport; }; diff --git a/include/linux/netfilter/xt_cluster.h b/include/linux/netfilter/xt_cluster.h index 886682656f09..9b883c8fbf54 100644 --- a/include/linux/netfilter/xt_cluster.h +++ b/include/linux/netfilter/xt_cluster.h @@ -1,15 +1,17 @@ #ifndef _XT_CLUSTER_MATCH_H #define _XT_CLUSTER_MATCH_H +#include <linux/types.h> + enum xt_cluster_flags { XT_CLUSTER_F_INV = (1 << 0) }; struct xt_cluster_match_info { - u_int32_t total_nodes; - u_int32_t node_mask; - u_int32_t hash_seed; - u_int32_t flags; + __u32 total_nodes; + __u32 node_mask; + __u32 hash_seed; + __u32 flags; }; #define XT_CLUSTER_NODES_MAX 32 diff --git a/include/linux/netfilter/xt_comment.h b/include/linux/netfilter/xt_comment.h index eacfedc6b5d0..0ea5e79f5bd7 100644 --- a/include/linux/netfilter/xt_comment.h +++ b/include/linux/netfilter/xt_comment.h @@ -4,7 +4,7 @@ #define XT_MAX_COMMENT_LEN 256 struct xt_comment_info { - unsigned char comment[XT_MAX_COMMENT_LEN]; + char comment[XT_MAX_COMMENT_LEN]; }; #endif /* XT_COMMENT_H */ diff --git a/include/linux/netfilter/xt_connlimit.h b/include/linux/netfilter/xt_connlimit.h index 7e3284bcbd2b..0ca66e97acbc 100644 --- a/include/linux/netfilter/xt_connlimit.h +++ b/include/linux/netfilter/xt_connlimit.h @@ -1,8 +1,15 @@ #ifndef _XT_CONNLIMIT_H #define _XT_CONNLIMIT_H +#include <linux/types.h> + struct xt_connlimit_data; +enum { + XT_CONNLIMIT_INVERT = 1 << 0, + XT_CONNLIMIT_DADDR = 1 << 1, +}; + struct xt_connlimit_info { union { union nf_inet_addr mask; @@ -13,7 +20,14 @@ struct xt_connlimit_info { }; #endif }; - unsigned int limit, inverse; + unsigned int limit; + union { + /* revision 0 */ + unsigned int inverse; + + /* revision 1 */ + __u32 flags; + }; /* Used internally by the kernel */ struct xt_connlimit_data *data __attribute__((aligned(8))); diff --git a/include/linux/netfilter/xt_conntrack.h b/include/linux/netfilter/xt_conntrack.h index 54f47a2f6152..74b904d8f99c 100644 --- a/include/linux/netfilter/xt_conntrack.h +++ b/include/linux/netfilter/xt_conntrack.h @@ -58,4 +58,19 @@ struct xt_conntrack_mtinfo2 { __u16 state_mask, status_mask; }; +struct xt_conntrack_mtinfo3 { + union nf_inet_addr origsrc_addr, origsrc_mask; + union nf_inet_addr origdst_addr, origdst_mask; + union nf_inet_addr replsrc_addr, replsrc_mask; + union nf_inet_addr repldst_addr, repldst_mask; + __u32 expires_min, expires_max; + __u16 l4proto; + __u16 origsrc_port, origdst_port; + __u16 replsrc_port, repldst_port; + __u16 match_flags, invert_flags; + __u16 state_mask, status_mask; + __u16 origsrc_port_high, origdst_port_high; + __u16 replsrc_port_high, repldst_port_high; +}; + #endif /*_XT_CONNTRACK_H*/ diff --git a/include/linux/netfilter/xt_devgroup.h b/include/linux/netfilter/xt_devgroup.h new file mode 100644 index 000000000000..1babde0ec900 --- /dev/null +++ b/include/linux/netfilter/xt_devgroup.h @@ -0,0 +1,21 @@ +#ifndef _XT_DEVGROUP_H +#define _XT_DEVGROUP_H + +#include <linux/types.h> + +enum xt_devgroup_flags { + XT_DEVGROUP_MATCH_SRC = 0x1, + XT_DEVGROUP_INVERT_SRC = 0x2, + XT_DEVGROUP_MATCH_DST = 0x4, + XT_DEVGROUP_INVERT_DST = 0x8, +}; + +struct xt_devgroup_info { + __u32 flags; + __u32 src_group; + __u32 src_mask; + __u32 dst_group; + __u32 dst_mask; +}; + +#endif /* _XT_DEVGROUP_H */ diff --git a/include/linux/netfilter/xt_quota.h b/include/linux/netfilter/xt_quota.h index b0d28c659ab7..ca6e03e47a17 100644 --- a/include/linux/netfilter/xt_quota.h +++ b/include/linux/netfilter/xt_quota.h @@ -1,6 +1,8 @@ #ifndef _XT_QUOTA_H #define _XT_QUOTA_H +#include <linux/types.h> + enum xt_quota_flags { XT_QUOTA_INVERT = 0x1, }; @@ -9,9 +11,9 @@ enum xt_quota_flags { struct xt_quota_priv; struct xt_quota_info { - u_int32_t flags; - u_int32_t pad; - aligned_u64 quota; + __u32 flags; + __u32 pad; + aligned_u64 quota; /* Used internally by the kernel */ struct xt_quota_priv *master; diff --git a/include/linux/netfilter/xt_set.h b/include/linux/netfilter/xt_set.h new file mode 100644 index 000000000000..081f1ded2842 --- /dev/null +++ b/include/linux/netfilter/xt_set.h @@ -0,0 +1,56 @@ +#ifndef _XT_SET_H +#define _XT_SET_H + +#include <linux/types.h> +#include <linux/netfilter/ipset/ip_set.h> + +/* Revision 0 interface: backward compatible with netfilter/iptables */ + +/* + * Option flags for kernel operations (xt_set_info_v0) + */ +#define IPSET_SRC 0x01 /* Source match/add */ +#define IPSET_DST 0x02 /* Destination match/add */ +#define IPSET_MATCH_INV 0x04 /* Inverse matching */ + +struct xt_set_info_v0 { + ip_set_id_t index; + union { + __u32 flags[IPSET_DIM_MAX + 1]; + struct { + __u32 __flags[IPSET_DIM_MAX]; + __u8 dim; + __u8 flags; + } compat; + } u; +}; + +/* match and target infos */ +struct xt_set_info_match_v0 { + struct xt_set_info_v0 match_set; +}; + +struct xt_set_info_target_v0 { + struct xt_set_info_v0 add_set; + struct xt_set_info_v0 del_set; +}; + +/* Revision 1: current interface to netfilter/iptables */ + +struct xt_set_info { + ip_set_id_t index; + __u8 dim; + __u8 flags; +}; + +/* match and target infos */ +struct xt_set_info_match { + struct xt_set_info match_set; +}; + +struct xt_set_info_target { + struct xt_set_info add_set; + struct xt_set_info del_set; +}; + +#endif /*_XT_SET_H*/ diff --git a/include/linux/netfilter/xt_socket.h b/include/linux/netfilter/xt_socket.h index 6f475b8ff34b..26d7217bd4f1 100644 --- a/include/linux/netfilter/xt_socket.h +++ b/include/linux/netfilter/xt_socket.h @@ -1,6 +1,8 @@ #ifndef _XT_SOCKET_H #define _XT_SOCKET_H +#include <linux/types.h> + enum { XT_SOCKET_TRANSPARENT = 1 << 0, }; diff --git a/include/linux/netfilter/xt_time.h b/include/linux/netfilter/xt_time.h index 14b6df412c9f..7c37fac576c4 100644 --- a/include/linux/netfilter/xt_time.h +++ b/include/linux/netfilter/xt_time.h @@ -1,14 +1,16 @@ #ifndef _XT_TIME_H #define _XT_TIME_H 1 +#include <linux/types.h> + struct xt_time_info { - u_int32_t date_start; - u_int32_t date_stop; - u_int32_t daytime_start; - u_int32_t daytime_stop; - u_int32_t monthdays_match; - u_int8_t weekdays_match; - u_int8_t flags; + __u32 date_start; + __u32 date_stop; + __u32 daytime_start; + __u32 daytime_stop; + __u32 monthdays_match; + __u8 weekdays_match; + __u8 flags; }; enum { diff --git a/include/linux/netfilter/xt_u32.h b/include/linux/netfilter/xt_u32.h index 9947f56cdbdd..04d1bfea03c2 100644 --- a/include/linux/netfilter/xt_u32.h +++ b/include/linux/netfilter/xt_u32.h @@ -1,6 +1,8 @@ #ifndef _XT_U32_H #define _XT_U32_H 1 +#include <linux/types.h> + enum xt_u32_ops { XT_U32_AND, XT_U32_LEFTSH, @@ -9,13 +11,13 @@ enum xt_u32_ops { }; struct xt_u32_location_element { - u_int32_t number; - u_int8_t nextop; + __u32 number; + __u8 nextop; }; struct xt_u32_value_element { - u_int32_t min; - u_int32_t max; + __u32 min; + __u32 max; }; /* @@ -27,14 +29,14 @@ struct xt_u32_value_element { struct xt_u32_test { struct xt_u32_location_element location[XT_U32_MAXSIZE+1]; struct xt_u32_value_element value[XT_U32_MAXSIZE+1]; - u_int8_t nnums; - u_int8_t nvalues; + __u8 nnums; + __u8 nvalues; }; struct xt_u32 { struct xt_u32_test tests[XT_U32_MAXSIZE+1]; - u_int8_t ntests; - u_int8_t invert; + __u8 ntests; + __u8 invert; }; #endif /* _XT_U32_H */ diff --git a/include/linux/netfilter_bridge/ebt_802_3.h b/include/linux/netfilter_bridge/ebt_802_3.h index c73ef0b18bdc..be5be1577a56 100644 --- a/include/linux/netfilter_bridge/ebt_802_3.h +++ b/include/linux/netfilter_bridge/ebt_802_3.h @@ -1,6 +1,8 @@ #ifndef __LINUX_BRIDGE_EBT_802_3_H #define __LINUX_BRIDGE_EBT_802_3_H +#include <linux/types.h> + #define EBT_802_3_SAP 0x01 #define EBT_802_3_TYPE 0x02 @@ -24,24 +26,24 @@ /* ui has one byte ctrl, ni has two */ struct hdr_ui { - uint8_t dsap; - uint8_t ssap; - uint8_t ctrl; - uint8_t orig[3]; + __u8 dsap; + __u8 ssap; + __u8 ctrl; + __u8 orig[3]; __be16 type; }; struct hdr_ni { - uint8_t dsap; - uint8_t ssap; + __u8 dsap; + __u8 ssap; __be16 ctrl; - uint8_t orig[3]; + __u8 orig[3]; __be16 type; }; struct ebt_802_3_hdr { - uint8_t daddr[6]; - uint8_t saddr[6]; + __u8 daddr[6]; + __u8 saddr[6]; __be16 len; union { struct hdr_ui ui; @@ -59,10 +61,10 @@ static inline struct ebt_802_3_hdr *ebt_802_3_hdr(const struct sk_buff *skb) #endif struct ebt_802_3_info { - uint8_t sap; + __u8 sap; __be16 type; - uint8_t bitmask; - uint8_t invflags; + __u8 bitmask; + __u8 invflags; }; #endif diff --git a/include/linux/netfilter_bridge/ebt_among.h b/include/linux/netfilter_bridge/ebt_among.h index 0009558609a7..bd4e3ad0b706 100644 --- a/include/linux/netfilter_bridge/ebt_among.h +++ b/include/linux/netfilter_bridge/ebt_among.h @@ -1,6 +1,8 @@ #ifndef __LINUX_BRIDGE_EBT_AMONG_H #define __LINUX_BRIDGE_EBT_AMONG_H +#include <linux/types.h> + #define EBT_AMONG_DST 0x01 #define EBT_AMONG_SRC 0x02 @@ -30,7 +32,7 @@ */ struct ebt_mac_wormhash_tuple { - uint32_t cmp[2]; + __u32 cmp[2]; __be32 ip; }; diff --git a/include/linux/netfilter_bridge/ebt_arp.h b/include/linux/netfilter_bridge/ebt_arp.h index cbf4843b6b0f..522f3e427f49 100644 --- a/include/linux/netfilter_bridge/ebt_arp.h +++ b/include/linux/netfilter_bridge/ebt_arp.h @@ -1,6 +1,8 @@ #ifndef __LINUX_BRIDGE_EBT_ARP_H #define __LINUX_BRIDGE_EBT_ARP_H +#include <linux/types.h> + #define EBT_ARP_OPCODE 0x01 #define EBT_ARP_HTYPE 0x02 #define EBT_ARP_PTYPE 0x04 @@ -27,8 +29,8 @@ struct ebt_arp_info unsigned char smmsk[ETH_ALEN]; unsigned char dmaddr[ETH_ALEN]; unsigned char dmmsk[ETH_ALEN]; - uint8_t bitmask; - uint8_t invflags; + __u8 bitmask; + __u8 invflags; }; #endif diff --git a/include/linux/netfilter_bridge/ebt_ip.h b/include/linux/netfilter_bridge/ebt_ip.h index 6a708fb92241..c4bbc41b0ea4 100644 --- a/include/linux/netfilter_bridge/ebt_ip.h +++ b/include/linux/netfilter_bridge/ebt_ip.h @@ -15,6 +15,8 @@ #ifndef __LINUX_BRIDGE_EBT_IP_H #define __LINUX_BRIDGE_EBT_IP_H +#include <linux/types.h> + #define EBT_IP_SOURCE 0x01 #define EBT_IP_DEST 0x02 #define EBT_IP_TOS 0x04 @@ -31,12 +33,12 @@ struct ebt_ip_info { __be32 daddr; __be32 smsk; __be32 dmsk; - uint8_t tos; - uint8_t protocol; - uint8_t bitmask; - uint8_t invflags; - uint16_t sport[2]; - uint16_t dport[2]; + __u8 tos; + __u8 protocol; + __u8 bitmask; + __u8 invflags; + __u16 sport[2]; + __u16 dport[2]; }; #endif diff --git a/include/linux/netfilter_bridge/ebt_ip6.h b/include/linux/netfilter_bridge/ebt_ip6.h index e5de98701519..42b889682721 100644 --- a/include/linux/netfilter_bridge/ebt_ip6.h +++ b/include/linux/netfilter_bridge/ebt_ip6.h @@ -12,14 +12,19 @@ #ifndef __LINUX_BRIDGE_EBT_IP6_H #define __LINUX_BRIDGE_EBT_IP6_H +#include <linux/types.h> + #define EBT_IP6_SOURCE 0x01 #define EBT_IP6_DEST 0x02 #define EBT_IP6_TCLASS 0x04 #define EBT_IP6_PROTO 0x08 #define EBT_IP6_SPORT 0x10 #define EBT_IP6_DPORT 0x20 +#define EBT_IP6_ICMP6 0x40 + #define EBT_IP6_MASK (EBT_IP6_SOURCE | EBT_IP6_DEST | EBT_IP6_TCLASS |\ - EBT_IP6_PROTO | EBT_IP6_SPORT | EBT_IP6_DPORT) + EBT_IP6_PROTO | EBT_IP6_SPORT | EBT_IP6_DPORT | \ + EBT_IP6_ICMP6) #define EBT_IP6_MATCH "ip6" /* the same values are used for the invflags */ @@ -28,12 +33,18 @@ struct ebt_ip6_info { struct in6_addr daddr; struct in6_addr smsk; struct in6_addr dmsk; - uint8_t tclass; - uint8_t protocol; - uint8_t bitmask; - uint8_t invflags; - uint16_t sport[2]; - uint16_t dport[2]; + __u8 tclass; + __u8 protocol; + __u8 bitmask; + __u8 invflags; + union { + __u16 sport[2]; + __u8 icmpv6_type[2]; + }; + union { + __u16 dport[2]; + __u8 icmpv6_code[2]; + }; }; #endif diff --git a/include/linux/netfilter_bridge/ebt_limit.h b/include/linux/netfilter_bridge/ebt_limit.h index 4bf76b751676..66d80b30ba0e 100644 --- a/include/linux/netfilter_bridge/ebt_limit.h +++ b/include/linux/netfilter_bridge/ebt_limit.h @@ -1,6 +1,8 @@ #ifndef __LINUX_BRIDGE_EBT_LIMIT_H #define __LINUX_BRIDGE_EBT_LIMIT_H +#include <linux/types.h> + #define EBT_LIMIT_MATCH "limit" /* timings are in milliseconds. */ @@ -10,13 +12,13 @@ seconds, or one every 59 hours. */ struct ebt_limit_info { - u_int32_t avg; /* Average secs between packets * scale */ - u_int32_t burst; /* Period multiplier for upper limit. */ + __u32 avg; /* Average secs between packets * scale */ + __u32 burst; /* Period multiplier for upper limit. */ /* Used internally by the kernel */ unsigned long prev; - u_int32_t credit; - u_int32_t credit_cap, cost; + __u32 credit; + __u32 credit_cap, cost; }; #endif diff --git a/include/linux/netfilter_bridge/ebt_log.h b/include/linux/netfilter_bridge/ebt_log.h index cc2cdfb764bc..7e7f1d1fe494 100644 --- a/include/linux/netfilter_bridge/ebt_log.h +++ b/include/linux/netfilter_bridge/ebt_log.h @@ -1,6 +1,8 @@ #ifndef __LINUX_BRIDGE_EBT_LOG_H #define __LINUX_BRIDGE_EBT_LOG_H +#include <linux/types.h> + #define EBT_LOG_IP 0x01 /* if the frame is made by ip, log the ip information */ #define EBT_LOG_ARP 0x02 #define EBT_LOG_NFLOG 0x04 @@ -10,9 +12,9 @@ #define EBT_LOG_WATCHER "log" struct ebt_log_info { - uint8_t loglevel; - uint8_t prefix[EBT_LOG_PREFIX_SIZE]; - uint32_t bitmask; + __u8 loglevel; + __u8 prefix[EBT_LOG_PREFIX_SIZE]; + __u32 bitmask; }; #endif diff --git a/include/linux/netfilter_bridge/ebt_mark_m.h b/include/linux/netfilter_bridge/ebt_mark_m.h index 9ceb10ec0ed6..410f9e5a71d4 100644 --- a/include/linux/netfilter_bridge/ebt_mark_m.h +++ b/include/linux/netfilter_bridge/ebt_mark_m.h @@ -1,13 +1,15 @@ #ifndef __LINUX_BRIDGE_EBT_MARK_M_H #define __LINUX_BRIDGE_EBT_MARK_M_H +#include <linux/types.h> + #define EBT_MARK_AND 0x01 #define EBT_MARK_OR 0x02 #define EBT_MARK_MASK (EBT_MARK_AND | EBT_MARK_OR) struct ebt_mark_m_info { unsigned long mark, mask; - uint8_t invert; - uint8_t bitmask; + __u8 invert; + __u8 bitmask; }; #define EBT_MARK_MATCH "mark_m" diff --git a/include/linux/netfilter_bridge/ebt_nflog.h b/include/linux/netfilter_bridge/ebt_nflog.h index 052817849b83..df829fce9125 100644 --- a/include/linux/netfilter_bridge/ebt_nflog.h +++ b/include/linux/netfilter_bridge/ebt_nflog.h @@ -1,6 +1,8 @@ #ifndef __LINUX_BRIDGE_EBT_NFLOG_H #define __LINUX_BRIDGE_EBT_NFLOG_H +#include <linux/types.h> + #define EBT_NFLOG_MASK 0x0 #define EBT_NFLOG_PREFIX_SIZE 64 @@ -10,11 +12,11 @@ #define EBT_NFLOG_DEFAULT_THRESHOLD 1 struct ebt_nflog_info { - u_int32_t len; - u_int16_t group; - u_int16_t threshold; - u_int16_t flags; - u_int16_t pad; + __u32 len; + __u16 group; + __u16 threshold; + __u16 flags; + __u16 pad; char prefix[EBT_NFLOG_PREFIX_SIZE]; }; diff --git a/include/linux/netfilter_bridge/ebt_pkttype.h b/include/linux/netfilter_bridge/ebt_pkttype.h index 51a799840931..c241badcd036 100644 --- a/include/linux/netfilter_bridge/ebt_pkttype.h +++ b/include/linux/netfilter_bridge/ebt_pkttype.h @@ -1,9 +1,11 @@ #ifndef __LINUX_BRIDGE_EBT_PKTTYPE_H #define __LINUX_BRIDGE_EBT_PKTTYPE_H +#include <linux/types.h> + struct ebt_pkttype_info { - uint8_t pkt_type; - uint8_t invert; + __u8 pkt_type; + __u8 invert; }; #define EBT_PKTTYPE_MATCH "pkttype" diff --git a/include/linux/netfilter_bridge/ebt_stp.h b/include/linux/netfilter_bridge/ebt_stp.h index e503a0aa2728..1025b9f5fb7d 100644 --- a/include/linux/netfilter_bridge/ebt_stp.h +++ b/include/linux/netfilter_bridge/ebt_stp.h @@ -1,6 +1,8 @@ #ifndef __LINUX_BRIDGE_EBT_STP_H #define __LINUX_BRIDGE_EBT_STP_H +#include <linux/types.h> + #define EBT_STP_TYPE 0x0001 #define EBT_STP_FLAGS 0x0002 @@ -21,24 +23,24 @@ #define EBT_STP_MATCH "stp" struct ebt_stp_config_info { - uint8_t flags; - uint16_t root_priol, root_priou; + __u8 flags; + __u16 root_priol, root_priou; char root_addr[6], root_addrmsk[6]; - uint32_t root_costl, root_costu; - uint16_t sender_priol, sender_priou; + __u32 root_costl, root_costu; + __u16 sender_priol, sender_priou; char sender_addr[6], sender_addrmsk[6]; - uint16_t portl, portu; - uint16_t msg_agel, msg_ageu; - uint16_t max_agel, max_ageu; - uint16_t hello_timel, hello_timeu; - uint16_t forward_delayl, forward_delayu; + __u16 portl, portu; + __u16 msg_agel, msg_ageu; + __u16 max_agel, max_ageu; + __u16 hello_timel, hello_timeu; + __u16 forward_delayl, forward_delayu; }; struct ebt_stp_info { - uint8_t type; + __u8 type; struct ebt_stp_config_info config; - uint16_t bitmask; - uint16_t invflags; + __u16 bitmask; + __u16 invflags; }; #endif diff --git a/include/linux/netfilter_bridge/ebt_ulog.h b/include/linux/netfilter_bridge/ebt_ulog.h index b677e2671541..89a6becb5269 100644 --- a/include/linux/netfilter_bridge/ebt_ulog.h +++ b/include/linux/netfilter_bridge/ebt_ulog.h @@ -1,6 +1,8 @@ #ifndef _EBT_ULOG_H #define _EBT_ULOG_H +#include <linux/types.h> + #define EBT_ULOG_DEFAULT_NLGROUP 0 #define EBT_ULOG_DEFAULT_QTHRESHOLD 1 #define EBT_ULOG_MAXNLGROUPS 32 /* hardcoded netlink max */ @@ -10,7 +12,7 @@ #define EBT_ULOG_VERSION 1 struct ebt_ulog_info { - uint32_t nlgroup; + __u32 nlgroup; unsigned int cprange; unsigned int qthreshold; char prefix[EBT_ULOG_PREFIX_LEN]; diff --git a/include/linux/netfilter_bridge/ebt_vlan.h b/include/linux/netfilter_bridge/ebt_vlan.h index 1d98be4031e7..967d1d5cf98d 100644 --- a/include/linux/netfilter_bridge/ebt_vlan.h +++ b/include/linux/netfilter_bridge/ebt_vlan.h @@ -1,6 +1,8 @@ #ifndef __LINUX_BRIDGE_EBT_VLAN_H #define __LINUX_BRIDGE_EBT_VLAN_H +#include <linux/types.h> + #define EBT_VLAN_ID 0x01 #define EBT_VLAN_PRIO 0x02 #define EBT_VLAN_ENCAP 0x04 @@ -8,12 +10,12 @@ #define EBT_VLAN_MATCH "vlan" struct ebt_vlan_info { - uint16_t id; /* VLAN ID {1-4095} */ - uint8_t prio; /* VLAN User Priority {0-7} */ + __u16 id; /* VLAN ID {1-4095} */ + __u8 prio; /* VLAN User Priority {0-7} */ __be16 encap; /* VLAN Encapsulated frame code {0-65535} */ - uint8_t bitmask; /* Args bitmask bit 1=1 - ID arg, + __u8 bitmask; /* Args bitmask bit 1=1 - ID arg, bit 2=1 User-Priority arg, bit 3=1 encap*/ - uint8_t invflags; /* Inverse bitmask bit 1=1 - inversed ID arg, + __u8 invflags; /* Inverse bitmask bit 1=1 - inversed ID arg, bit 2=1 - inversed Pirority arg */ }; diff --git a/include/linux/netfilter_ipv4/ipt_CLUSTERIP.h b/include/linux/netfilter_ipv4/ipt_CLUSTERIP.h index e5a3687c8a72..c6a204c97047 100644 --- a/include/linux/netfilter_ipv4/ipt_CLUSTERIP.h +++ b/include/linux/netfilter_ipv4/ipt_CLUSTERIP.h @@ -1,6 +1,8 @@ #ifndef _IPT_CLUSTERIP_H_target #define _IPT_CLUSTERIP_H_target +#include <linux/types.h> + enum clusterip_hashmode { CLUSTERIP_HASHMODE_SIP = 0, CLUSTERIP_HASHMODE_SIP_SPT, @@ -17,15 +19,15 @@ struct clusterip_config; struct ipt_clusterip_tgt_info { - u_int32_t flags; + __u32 flags; /* only relevant for new ones */ - u_int8_t clustermac[6]; - u_int16_t num_total_nodes; - u_int16_t num_local_nodes; - u_int16_t local_nodes[CLUSTERIP_MAX_NODES]; - u_int32_t hash_mode; - u_int32_t hash_initval; + __u8 clustermac[6]; + __u16 num_total_nodes; + __u16 num_local_nodes; + __u16 local_nodes[CLUSTERIP_MAX_NODES]; + __u32 hash_mode; + __u32 hash_initval; /* Used internally by the kernel */ struct clusterip_config *config; diff --git a/include/linux/netfilter_ipv4/ipt_ECN.h b/include/linux/netfilter_ipv4/ipt_ECN.h index 7ca45918ab8e..bb88d5315a4d 100644 --- a/include/linux/netfilter_ipv4/ipt_ECN.h +++ b/include/linux/netfilter_ipv4/ipt_ECN.h @@ -8,6 +8,8 @@ */ #ifndef _IPT_ECN_TARGET_H #define _IPT_ECN_TARGET_H + +#include <linux/types.h> #include <linux/netfilter/xt_DSCP.h> #define IPT_ECN_IP_MASK (~XT_DSCP_MASK) @@ -19,11 +21,11 @@ #define IPT_ECN_OP_MASK 0xce struct ipt_ECN_info { - u_int8_t operation; /* bitset of operations */ - u_int8_t ip_ect; /* ECT codepoint of IPv4 header, pre-shifted */ + __u8 operation; /* bitset of operations */ + __u8 ip_ect; /* ECT codepoint of IPv4 header, pre-shifted */ union { struct { - u_int8_t ece:1, cwr:1; /* TCP ECT bits */ + __u8 ece:1, cwr:1; /* TCP ECT bits */ } tcp; } proto; }; diff --git a/include/linux/netfilter_ipv4/ipt_SAME.h b/include/linux/netfilter_ipv4/ipt_SAME.h index 2529660c5b38..5bca78267afd 100644 --- a/include/linux/netfilter_ipv4/ipt_SAME.h +++ b/include/linux/netfilter_ipv4/ipt_SAME.h @@ -1,15 +1,17 @@ #ifndef _IPT_SAME_H #define _IPT_SAME_H +#include <linux/types.h> + #define IPT_SAME_MAX_RANGE 10 #define IPT_SAME_NODST 0x01 struct ipt_same_info { unsigned char info; - u_int32_t rangesize; - u_int32_t ipnum; - u_int32_t *iparray; + __u32 rangesize; + __u32 ipnum; + __u32 *iparray; /* hangs off end. */ struct nf_nat_range range[IPT_SAME_MAX_RANGE]; diff --git a/include/linux/netfilter_ipv4/ipt_TTL.h b/include/linux/netfilter_ipv4/ipt_TTL.h index ee6611edc112..f6ac169d92f9 100644 --- a/include/linux/netfilter_ipv4/ipt_TTL.h +++ b/include/linux/netfilter_ipv4/ipt_TTL.h @@ -4,6 +4,8 @@ #ifndef _IPT_TTL_H #define _IPT_TTL_H +#include <linux/types.h> + enum { IPT_TTL_SET = 0, IPT_TTL_INC, @@ -13,8 +15,8 @@ enum { #define IPT_TTL_MAXMODE IPT_TTL_DEC struct ipt_TTL_info { - u_int8_t mode; - u_int8_t ttl; + __u8 mode; + __u8 ttl; }; diff --git a/include/linux/netfilter_ipv4/ipt_addrtype.h b/include/linux/netfilter_ipv4/ipt_addrtype.h index 446de6aef983..0da42237c8da 100644 --- a/include/linux/netfilter_ipv4/ipt_addrtype.h +++ b/include/linux/netfilter_ipv4/ipt_addrtype.h @@ -1,6 +1,8 @@ #ifndef _IPT_ADDRTYPE_H #define _IPT_ADDRTYPE_H +#include <linux/types.h> + enum { IPT_ADDRTYPE_INVERT_SOURCE = 0x0001, IPT_ADDRTYPE_INVERT_DEST = 0x0002, @@ -9,17 +11,17 @@ enum { }; struct ipt_addrtype_info_v1 { - u_int16_t source; /* source-type mask */ - u_int16_t dest; /* dest-type mask */ - u_int32_t flags; + __u16 source; /* source-type mask */ + __u16 dest; /* dest-type mask */ + __u32 flags; }; /* revision 0 */ struct ipt_addrtype_info { - u_int16_t source; /* source-type mask */ - u_int16_t dest; /* dest-type mask */ - u_int32_t invert_source; - u_int32_t invert_dest; + __u16 source; /* source-type mask */ + __u16 dest; /* dest-type mask */ + __u32 invert_source; + __u32 invert_dest; }; #endif diff --git a/include/linux/netfilter_ipv4/ipt_ah.h b/include/linux/netfilter_ipv4/ipt_ah.h index 2e555b4d05e3..4e02bb0119e3 100644 --- a/include/linux/netfilter_ipv4/ipt_ah.h +++ b/include/linux/netfilter_ipv4/ipt_ah.h @@ -1,9 +1,11 @@ #ifndef _IPT_AH_H #define _IPT_AH_H +#include <linux/types.h> + struct ipt_ah { - u_int32_t spis[2]; /* Security Parameter Index */ - u_int8_t invflags; /* Inverse flags */ + __u32 spis[2]; /* Security Parameter Index */ + __u8 invflags; /* Inverse flags */ }; diff --git a/include/linux/netfilter_ipv4/ipt_ecn.h b/include/linux/netfilter_ipv4/ipt_ecn.h index 9945baa4ccd7..eabf95fb7d3e 100644 --- a/include/linux/netfilter_ipv4/ipt_ecn.h +++ b/include/linux/netfilter_ipv4/ipt_ecn.h @@ -8,6 +8,8 @@ */ #ifndef _IPT_ECN_H #define _IPT_ECN_H + +#include <linux/types.h> #include <linux/netfilter/xt_dscp.h> #define IPT_ECN_IP_MASK (~XT_DSCP_MASK) @@ -20,12 +22,12 @@ /* match info */ struct ipt_ecn_info { - u_int8_t operation; - u_int8_t invert; - u_int8_t ip_ect; + __u8 operation; + __u8 invert; + __u8 ip_ect; union { struct { - u_int8_t ect; + __u8 ect; } tcp; } proto; }; diff --git a/include/linux/netfilter_ipv4/ipt_ttl.h b/include/linux/netfilter_ipv4/ipt_ttl.h index ee24fd86a3aa..37bee4442486 100644 --- a/include/linux/netfilter_ipv4/ipt_ttl.h +++ b/include/linux/netfilter_ipv4/ipt_ttl.h @@ -4,6 +4,8 @@ #ifndef _IPT_TTL_H #define _IPT_TTL_H +#include <linux/types.h> + enum { IPT_TTL_EQ = 0, /* equals */ IPT_TTL_NE, /* not equals */ @@ -13,8 +15,8 @@ enum { struct ipt_ttl_info { - u_int8_t mode; - u_int8_t ttl; + __u8 mode; + __u8 ttl; }; diff --git a/include/linux/netfilter_ipv6/ip6t_HL.h b/include/linux/netfilter_ipv6/ip6t_HL.h index afb7813d45ab..ebd8ead1bb63 100644 --- a/include/linux/netfilter_ipv6/ip6t_HL.h +++ b/include/linux/netfilter_ipv6/ip6t_HL.h @@ -5,6 +5,8 @@ #ifndef _IP6T_HL_H #define _IP6T_HL_H +#include <linux/types.h> + enum { IP6T_HL_SET = 0, IP6T_HL_INC, @@ -14,8 +16,8 @@ enum { #define IP6T_HL_MAXMODE IP6T_HL_DEC struct ip6t_HL_info { - u_int8_t mode; - u_int8_t hop_limit; + __u8 mode; + __u8 hop_limit; }; diff --git a/include/linux/netfilter_ipv6/ip6t_REJECT.h b/include/linux/netfilter_ipv6/ip6t_REJECT.h index 6be6504162bb..205ed62e4605 100644 --- a/include/linux/netfilter_ipv6/ip6t_REJECT.h +++ b/include/linux/netfilter_ipv6/ip6t_REJECT.h @@ -1,6 +1,8 @@ #ifndef _IP6T_REJECT_H #define _IP6T_REJECT_H +#include <linux/types.h> + enum ip6t_reject_with { IP6T_ICMP6_NO_ROUTE, IP6T_ICMP6_ADM_PROHIBITED, @@ -12,7 +14,7 @@ enum ip6t_reject_with { }; struct ip6t_reject_info { - u_int32_t with; /* reject type */ + __u32 with; /* reject type */ }; #endif /*_IP6T_REJECT_H*/ diff --git a/include/linux/netfilter_ipv6/ip6t_ah.h b/include/linux/netfilter_ipv6/ip6t_ah.h index 17a745cfb2c7..5da2b65cb3ad 100644 --- a/include/linux/netfilter_ipv6/ip6t_ah.h +++ b/include/linux/netfilter_ipv6/ip6t_ah.h @@ -1,11 +1,13 @@ #ifndef _IP6T_AH_H #define _IP6T_AH_H +#include <linux/types.h> + struct ip6t_ah { - u_int32_t spis[2]; /* Security Parameter Index */ - u_int32_t hdrlen; /* Header Length */ - u_int8_t hdrres; /* Test of the Reserved Filed */ - u_int8_t invflags; /* Inverse flags */ + __u32 spis[2]; /* Security Parameter Index */ + __u32 hdrlen; /* Header Length */ + __u8 hdrres; /* Test of the Reserved Filed */ + __u8 invflags; /* Inverse flags */ }; #define IP6T_AH_SPI 0x01 diff --git a/include/linux/netfilter_ipv6/ip6t_frag.h b/include/linux/netfilter_ipv6/ip6t_frag.h index 3724d0850920..b47f61b9e082 100644 --- a/include/linux/netfilter_ipv6/ip6t_frag.h +++ b/include/linux/netfilter_ipv6/ip6t_frag.h @@ -1,11 +1,13 @@ #ifndef _IP6T_FRAG_H #define _IP6T_FRAG_H +#include <linux/types.h> + struct ip6t_frag { - u_int32_t ids[2]; /* Security Parameter Index */ - u_int32_t hdrlen; /* Header Length */ - u_int8_t flags; /* */ - u_int8_t invflags; /* Inverse flags */ + __u32 ids[2]; /* Security Parameter Index */ + __u32 hdrlen; /* Header Length */ + __u8 flags; /* */ + __u8 invflags; /* Inverse flags */ }; #define IP6T_FRAG_IDS 0x01 diff --git a/include/linux/netfilter_ipv6/ip6t_hl.h b/include/linux/netfilter_ipv6/ip6t_hl.h index 5ef91b8319a8..6e76dbc6c19a 100644 --- a/include/linux/netfilter_ipv6/ip6t_hl.h +++ b/include/linux/netfilter_ipv6/ip6t_hl.h @@ -5,6 +5,8 @@ #ifndef _IP6T_HL_H #define _IP6T_HL_H +#include <linux/types.h> + enum { IP6T_HL_EQ = 0, /* equals */ IP6T_HL_NE, /* not equals */ @@ -14,8 +16,8 @@ enum { struct ip6t_hl_info { - u_int8_t mode; - u_int8_t hop_limit; + __u8 mode; + __u8 hop_limit; }; diff --git a/include/linux/netfilter_ipv6/ip6t_ipv6header.h b/include/linux/netfilter_ipv6/ip6t_ipv6header.h index 01dfd445596a..efae3a20c214 100644 --- a/include/linux/netfilter_ipv6/ip6t_ipv6header.h +++ b/include/linux/netfilter_ipv6/ip6t_ipv6header.h @@ -8,10 +8,12 @@ on whether they contain certain headers */ #ifndef __IPV6HEADER_H #define __IPV6HEADER_H +#include <linux/types.h> + struct ip6t_ipv6header_info { - u_int8_t matchflags; - u_int8_t invflags; - u_int8_t modeflag; + __u8 matchflags; + __u8 invflags; + __u8 modeflag; }; #define MASK_HOPOPTS 128 diff --git a/include/linux/netfilter_ipv6/ip6t_mh.h b/include/linux/netfilter_ipv6/ip6t_mh.h index 18549bca2d1f..a7729a5025cd 100644 --- a/include/linux/netfilter_ipv6/ip6t_mh.h +++ b/include/linux/netfilter_ipv6/ip6t_mh.h @@ -1,10 +1,12 @@ #ifndef _IP6T_MH_H #define _IP6T_MH_H +#include <linux/types.h> + /* MH matching stuff */ struct ip6t_mh { - u_int8_t types[2]; /* MH type range */ - u_int8_t invflags; /* Inverse flags */ + __u8 types[2]; /* MH type range */ + __u8 invflags; /* Inverse flags */ }; /* Values for "invflags" field in struct ip6t_mh. */ diff --git a/include/linux/netfilter_ipv6/ip6t_opts.h b/include/linux/netfilter_ipv6/ip6t_opts.h index 62d89bcd9f9c..17d419a811fd 100644 --- a/include/linux/netfilter_ipv6/ip6t_opts.h +++ b/include/linux/netfilter_ipv6/ip6t_opts.h @@ -1,14 +1,16 @@ #ifndef _IP6T_OPTS_H #define _IP6T_OPTS_H +#include <linux/types.h> + #define IP6T_OPTS_OPTSNR 16 struct ip6t_opts { - u_int32_t hdrlen; /* Header Length */ - u_int8_t flags; /* */ - u_int8_t invflags; /* Inverse flags */ - u_int16_t opts[IP6T_OPTS_OPTSNR]; /* opts */ - u_int8_t optsnr; /* Nr of OPts */ + __u32 hdrlen; /* Header Length */ + __u8 flags; /* */ + __u8 invflags; /* Inverse flags */ + __u16 opts[IP6T_OPTS_OPTSNR]; /* opts */ + __u8 optsnr; /* Nr of OPts */ }; #define IP6T_OPTS_LEN 0x01 diff --git a/include/linux/netfilter_ipv6/ip6t_rt.h b/include/linux/netfilter_ipv6/ip6t_rt.h index ab91bfd2cd00..7605a5ff81cd 100644 --- a/include/linux/netfilter_ipv6/ip6t_rt.h +++ b/include/linux/netfilter_ipv6/ip6t_rt.h @@ -1,18 +1,19 @@ #ifndef _IP6T_RT_H #define _IP6T_RT_H +#include <linux/types.h> /*#include <linux/in6.h>*/ #define IP6T_RT_HOPS 16 struct ip6t_rt { - u_int32_t rt_type; /* Routing Type */ - u_int32_t segsleft[2]; /* Segments Left */ - u_int32_t hdrlen; /* Header Length */ - u_int8_t flags; /* */ - u_int8_t invflags; /* Inverse flags */ + __u32 rt_type; /* Routing Type */ + __u32 segsleft[2]; /* Segments Left */ + __u32 hdrlen; /* Header Length */ + __u8 flags; /* */ + __u8 invflags; /* Inverse flags */ struct in6_addr addrs[IP6T_RT_HOPS]; /* Hops */ - u_int8_t addrnr; /* Nr of Addresses */ + __u8 addrnr; /* Nr of Addresses */ }; #define IP6T_RT_TYP 0x01 diff --git a/include/linux/pkt_sched.h b/include/linux/pkt_sched.h index 2cfa4bc8dea6..d4bb6f58c90c 100644 --- a/include/linux/pkt_sched.h +++ b/include/linux/pkt_sched.h @@ -247,6 +247,35 @@ struct tc_gred_sopt { __u16 pad1; }; +/* CHOKe section */ + +enum { + TCA_CHOKE_UNSPEC, + TCA_CHOKE_PARMS, + TCA_CHOKE_STAB, + __TCA_CHOKE_MAX, +}; + +#define TCA_CHOKE_MAX (__TCA_CHOKE_MAX - 1) + +struct tc_choke_qopt { + __u32 limit; /* Hard queue length (packets) */ + __u32 qth_min; /* Min average threshold (packets) */ + __u32 qth_max; /* Max average threshold (packets) */ + unsigned char Wlog; /* log(W) */ + unsigned char Plog; /* log(P_max/(qth_max-qth_min)) */ + unsigned char Scell_log; /* cell size for idle damping */ + unsigned char flags; /* see RED flags */ +}; + +struct tc_choke_xstats { + __u32 early; /* Early drops */ + __u32 pdrop; /* Drops due to queue limits */ + __u32 other; /* Drops due to drop() calls */ + __u32 marked; /* Marked packets */ + __u32 matched; /* Drops due to flow match */ +}; + /* HTB section */ #define TC_HTB_NUMPRIO 8 #define TC_HTB_MAXDEPTH 8 @@ -481,4 +510,16 @@ struct tc_drr_stats { __u32 deficit; }; +/* MQPRIO */ +#define TC_QOPT_BITMASK 15 +#define TC_QOPT_MAX_QUEUE 16 + +struct tc_mqprio_qopt { + __u8 num_tc; + __u8 prio_tc_map[TC_QOPT_BITMASK + 1]; + __u8 hw; + __u16 count[TC_QOPT_MAX_QUEUE]; + __u16 offset[TC_QOPT_MAX_QUEUE]; +}; + #endif diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index bf221d65d9ad..31f02d0b46a7 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1801,6 +1801,15 @@ static inline int pskb_trim_rcsum(struct sk_buff *skb, unsigned int len) prefetch(skb->prev), (skb != (struct sk_buff *)(queue)); \ skb = skb->prev) +#define skb_queue_reverse_walk_safe(queue, skb, tmp) \ + for (skb = (queue)->prev, tmp = skb->prev; \ + skb != (struct sk_buff *)(queue); \ + skb = tmp, tmp = skb->prev) + +#define skb_queue_reverse_walk_from_safe(queue, skb, tmp) \ + for (tmp = skb->prev; \ + skb != (struct sk_buff *)(queue); \ + skb = tmp, tmp = skb->prev) static inline bool skb_has_frag_list(const struct sk_buff *skb) { @@ -1868,7 +1877,7 @@ extern void skb_split(struct sk_buff *skb, extern int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen); -extern struct sk_buff *skb_segment(struct sk_buff *skb, int features); +extern struct sk_buff *skb_segment(struct sk_buff *skb, u32 features); static inline void *skb_header_pointer(const struct sk_buff *skb, int offset, int len, void *buffer) diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 1322695beb52..679a0494b5f2 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1790,8 +1790,9 @@ static inline void *wdev_priv(struct wireless_dev *wdev) /** * ieee80211_channel_to_frequency - convert channel number to frequency * @chan: channel number + * @band: band, necessary due to channel number overlap */ -extern int ieee80211_channel_to_frequency(int chan); +extern int ieee80211_channel_to_frequency(int chan, enum ieee80211_band band); /** * ieee80211_frequency_to_channel - convert frequency to channel number diff --git a/include/net/dst.h b/include/net/dst.h index 93b0310317be..484f80b69ada 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -40,24 +40,10 @@ struct dst_entry { struct rcu_head rcu_head; struct dst_entry *child; struct net_device *dev; - short error; - short obsolete; - int flags; -#define DST_HOST 0x0001 -#define DST_NOXFRM 0x0002 -#define DST_NOPOLICY 0x0004 -#define DST_NOHASH 0x0008 -#define DST_NOCACHE 0x0010 + struct dst_ops *ops; + unsigned long _metrics; unsigned long expires; - - unsigned short header_len; /* more space at head required */ - unsigned short trailer_len; /* space to reserve at tail */ - - unsigned int rate_tokens; - unsigned long rate_last; /* rate limiting for ICMP */ - struct dst_entry *path; - struct neighbour *neighbour; struct hh_cache *hh; #ifdef CONFIG_XFRM @@ -68,17 +54,16 @@ struct dst_entry { int (*input)(struct sk_buff*); int (*output)(struct sk_buff*); - struct dst_ops *ops; - - u32 _metrics[RTAX_MAX]; - -#ifdef CONFIG_NET_CLS_ROUTE + short error; + short obsolete; + unsigned short header_len; /* more space at head required */ + unsigned short trailer_len; /* space to reserve at tail */ +#ifdef CONFIG_IP_ROUTE_CLASSID __u32 tclassid; #else __u32 __pad2; #endif - /* * Align __refcnt to a 64 bytes alignment * (L1_CACHE_SIZE would be too much) @@ -93,6 +78,14 @@ struct dst_entry { atomic_t __refcnt; /* client references */ int __use; unsigned long lastuse; + unsigned long rate_last; /* rate limiting for ICMP */ + unsigned int rate_tokens; + int flags; +#define DST_HOST 0x0001 +#define DST_NOXFRM 0x0002 +#define DST_NOPOLICY 0x0004 +#define DST_NOHASH 0x0008 +#define DST_NOCACHE 0x0010 union { struct dst_entry *next; struct rtable __rcu *rt_next; @@ -103,10 +96,70 @@ struct dst_entry { #ifdef __KERNEL__ +extern u32 *dst_cow_metrics_generic(struct dst_entry *dst, unsigned long old); +extern const u32 dst_default_metrics[RTAX_MAX]; + +#define DST_METRICS_READ_ONLY 0x1UL +#define __DST_METRICS_PTR(Y) \ + ((u32 *)((Y) & ~DST_METRICS_READ_ONLY)) +#define DST_METRICS_PTR(X) __DST_METRICS_PTR((X)->_metrics) + +static inline bool dst_metrics_read_only(const struct dst_entry *dst) +{ + return dst->_metrics & DST_METRICS_READ_ONLY; +} + +extern void __dst_destroy_metrics_generic(struct dst_entry *dst, unsigned long old); + +static inline void dst_destroy_metrics_generic(struct dst_entry *dst) +{ + unsigned long val = dst->_metrics; + if (!(val & DST_METRICS_READ_ONLY)) + __dst_destroy_metrics_generic(dst, val); +} + +static inline u32 *dst_metrics_write_ptr(struct dst_entry *dst) +{ + unsigned long p = dst->_metrics; + + if (p & DST_METRICS_READ_ONLY) + return dst->ops->cow_metrics(dst, p); + return __DST_METRICS_PTR(p); +} + +/* This may only be invoked before the entry has reached global + * visibility. + */ +static inline void dst_init_metrics(struct dst_entry *dst, + const u32 *src_metrics, + bool read_only) +{ + dst->_metrics = ((unsigned long) src_metrics) | + (read_only ? DST_METRICS_READ_ONLY : 0); +} + +static inline void dst_copy_metrics(struct dst_entry *dest, const struct dst_entry *src) +{ + u32 *dst_metrics = dst_metrics_write_ptr(dest); + + if (dst_metrics) { + u32 *src_metrics = DST_METRICS_PTR(src); + + memcpy(dst_metrics, src_metrics, RTAX_MAX * sizeof(u32)); + } +} + +static inline u32 *dst_metrics_ptr(struct dst_entry *dst) +{ + return DST_METRICS_PTR(dst); +} + static inline u32 dst_metric_raw(const struct dst_entry *dst, const int metric) { - return dst->_metrics[metric-1]; + u32 *p = DST_METRICS_PTR(dst); + + return p[metric-1]; } static inline u32 @@ -131,22 +184,10 @@ dst_metric_advmss(const struct dst_entry *dst) static inline void dst_metric_set(struct dst_entry *dst, int metric, u32 val) { - dst->_metrics[metric-1] = val; -} - -static inline void dst_import_metrics(struct dst_entry *dst, const u32 *src_metrics) -{ - memcpy(dst->_metrics, src_metrics, RTAX_MAX * sizeof(u32)); -} + u32 *p = dst_metrics_write_ptr(dst); -static inline void dst_copy_metrics(struct dst_entry *dest, const struct dst_entry *src) -{ - dst_import_metrics(dest, src->_metrics); -} - -static inline u32 *dst_metrics_ptr(struct dst_entry *dst) -{ - return dst->_metrics; + if (p) + p[metric-1] = val; } static inline u32 diff --git a/include/net/dst_ops.h b/include/net/dst_ops.h index 21a320b8708e..dc0746328947 100644 --- a/include/net/dst_ops.h +++ b/include/net/dst_ops.h @@ -18,6 +18,7 @@ struct dst_ops { struct dst_entry * (*check)(struct dst_entry *, __u32 cookie); unsigned int (*default_advmss)(const struct dst_entry *); unsigned int (*default_mtu)(const struct dst_entry *); + u32 * (*cow_metrics)(struct dst_entry *, unsigned long); void (*destroy)(struct dst_entry *); void (*ifdown)(struct dst_entry *, struct net_device *dev, int how); diff --git a/include/net/flow.h b/include/net/flow.h index 240b7f356c71..1ae901f24436 100644 --- a/include/net/flow.h +++ b/include/net/flow.h @@ -48,7 +48,8 @@ struct flowi { __u8 proto; __u8 flags; -#define FLOWI_FLAG_ANYSRC 0x01 +#define FLOWI_FLAG_ANYSRC 0x01 +#define FLOWI_FLAG_PRECOW_METRICS 0x02 union { struct { __be16 sport; diff --git a/include/net/ieee80211_radiotap.h b/include/net/ieee80211_radiotap.h index af49f8ab7f81..b0be5fb9de19 100644 --- a/include/net/ieee80211_radiotap.h +++ b/include/net/ieee80211_radiotap.h @@ -178,6 +178,11 @@ struct ieee80211_radiotap_header { * * Number of unicast retries a transmitted frame used. * + * IEEE80211_RADIOTAP_MCS u8, u8, u8 unitless + * + * Contains a bitmap of known fields/flags, the flags, and + * the MCS index. + * */ enum ieee80211_radiotap_type { IEEE80211_RADIOTAP_TSFT = 0, @@ -199,6 +204,8 @@ enum ieee80211_radiotap_type { IEEE80211_RADIOTAP_RTS_RETRIES = 16, IEEE80211_RADIOTAP_DATA_RETRIES = 17, + IEEE80211_RADIOTAP_MCS = 19, + /* valid in every it_present bitmap, even vendor namespaces */ IEEE80211_RADIOTAP_RADIOTAP_NAMESPACE = 29, IEEE80211_RADIOTAP_VENDOR_NAMESPACE = 30, @@ -245,6 +252,24 @@ enum ieee80211_radiotap_type { #define IEEE80211_RADIOTAP_F_TX_CTS 0x0002 /* used cts 'protection' */ #define IEEE80211_RADIOTAP_F_TX_RTS 0x0004 /* used rts/cts handshake */ + +/* For IEEE80211_RADIOTAP_MCS */ +#define IEEE80211_RADIOTAP_MCS_HAVE_BW 0x01 +#define IEEE80211_RADIOTAP_MCS_HAVE_MCS 0x02 +#define IEEE80211_RADIOTAP_MCS_HAVE_GI 0x04 +#define IEEE80211_RADIOTAP_MCS_HAVE_FMT 0x08 +#define IEEE80211_RADIOTAP_MCS_HAVE_FEC 0x10 + +#define IEEE80211_RADIOTAP_MCS_BW_MASK 0x03 +#define IEEE80211_RADIOTAP_MCS_BW_20 0 +#define IEEE80211_RADIOTAP_MCS_BW_40 1 +#define IEEE80211_RADIOTAP_MCS_BW_20L 2 +#define IEEE80211_RADIOTAP_MCS_BW_20U 3 +#define IEEE80211_RADIOTAP_MCS_SGI 0x04 +#define IEEE80211_RADIOTAP_MCS_FMT_GF 0x08 +#define IEEE80211_RADIOTAP_MCS_FEC_LDPC 0x10 + + /* Ugly macro to convert literal channel numbers into their mhz equivalents * There are certianly some conditions that will break this (like feeding it '30') * but they shouldn't arise since nothing talks on channel 30. */ diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index 8181498fa96c..6e6dfd757682 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -219,7 +219,13 @@ static inline struct request_sock *inet_reqsk_alloc(struct request_sock_ops *ops static inline __u8 inet_sk_flowi_flags(const struct sock *sk) { - return inet_sk(sk)->transparent ? FLOWI_FLAG_ANYSRC : 0; + __u8 flags = 0; + + if (inet_sk(sk)->transparent) + flags |= FLOWI_FLAG_ANYSRC; + if (sk->sk_protocol == IPPROTO_TCP) + flags |= FLOWI_FLAG_PRECOW_METRICS; + return flags; } #endif /* _INET_SOCK_H */ diff --git a/include/net/inetpeer.h b/include/net/inetpeer.h index 599d96e74114..61f2c66edb2a 100644 --- a/include/net/inetpeer.h +++ b/include/net/inetpeer.h @@ -11,6 +11,7 @@ #include <linux/init.h> #include <linux/jiffies.h> #include <linux/spinlock.h> +#include <linux/rtnetlink.h> #include <net/ipv6.h> #include <asm/atomic.h> @@ -33,8 +34,8 @@ struct inet_peer { atomic_t refcnt; /* * Once inet_peer is queued for deletion (refcnt == -1), following fields - * are not available: rid, ip_id_count, tcp_ts, tcp_ts_stamp - * We can share memory with rcu_head to keep inet_peer small + * are not available: rid, ip_id_count, tcp_ts, tcp_ts_stamp, metrics + * We can share memory with rcu_head to help keep inet_peer small. */ union { struct { @@ -42,6 +43,7 @@ struct inet_peer { atomic_t ip_id_count; /* IP ID for the next packet */ __u32 tcp_ts; __u32 tcp_ts_stamp; + u32 metrics[RTAX_MAX]; }; struct rcu_head rcu; }; @@ -49,6 +51,13 @@ struct inet_peer { void inet_initpeers(void) __init; +#define INETPEER_METRICS_NEW (~(u32) 0) + +static inline bool inet_metrics_new(const struct inet_peer *p) +{ + return p->metrics[RTAX_LOCK-1] == INETPEER_METRICS_NEW; +} + /* can be called with or without local BH being disabled */ struct inet_peer *inet_getpeer(struct inetpeer_addr *daddr, int create); diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index 07bdb5e9e8ac..08b46b8c3031 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -55,7 +55,7 @@ struct fib_nh { int nh_weight; int nh_power; #endif -#ifdef CONFIG_NET_CLS_ROUTE +#ifdef CONFIG_IP_ROUTE_CLASSID __u32 nh_tclassid; #endif int nh_oif; @@ -77,7 +77,7 @@ struct fib_info { int fib_protocol; __be32 fib_prefsrc; u32 fib_priority; - u32 fib_metrics[RTAX_MAX]; + u32 *fib_metrics; #define fib_mtu fib_metrics[RTAX_MTU-1] #define fib_window fib_metrics[RTAX_WINDOW-1] #define fib_rtt fib_metrics[RTAX_RTT-1] @@ -96,12 +96,15 @@ struct fib_info { struct fib_rule; #endif +struct fib_table; struct fib_result { unsigned char prefixlen; unsigned char nh_sel; unsigned char type; unsigned char scope; struct fib_info *fi; + struct fib_table *table; + struct list_head *fa_head; #ifdef CONFIG_IP_MULTIPLE_TABLES struct fib_rule *r; #endif @@ -155,9 +158,6 @@ extern int fib_table_delete(struct fib_table *, struct fib_config *); extern int fib_table_dump(struct fib_table *table, struct sk_buff *skb, struct netlink_callback *cb); extern int fib_table_flush(struct fib_table *table); -extern void fib_table_select_default(struct fib_table *table, - const struct flowi *flp, - struct fib_result *res); extern void fib_free_table(struct fib_table *tb); @@ -201,7 +201,7 @@ static inline int fib_lookup(struct net *net, const struct flowi *flp, extern int __net_init fib4_rules_init(struct net *net); extern void __net_exit fib4_rules_exit(struct net *net); -#ifdef CONFIG_NET_CLS_ROUTE +#ifdef CONFIG_IP_ROUTE_CLASSID extern u32 fib_rules_tclass(struct fib_result *res); #endif @@ -218,8 +218,7 @@ extern void ip_fib_init(void); extern int fib_validate_source(__be32 src, __be32 dst, u8 tos, int oif, struct net_device *dev, __be32 *spec_dst, u32 *itag, u32 mark); -extern void fib_select_default(struct net *net, const struct flowi *flp, - struct fib_result *res); +extern void fib_select_default(struct fib_result *res); /* Exported by fib_semantics.c */ extern int ip_fib_check_default(__be32 gw, struct net_device *dev); @@ -229,13 +228,13 @@ extern int fib_sync_up(struct net_device *dev); extern __be32 __fib_res_prefsrc(struct fib_result *res); extern void fib_select_multipath(const struct flowi *flp, struct fib_result *res); -/* Exported by fib_{hash|trie}.c */ -extern void fib_hash_init(void); -extern struct fib_table *fib_hash_table(u32 id); +/* Exported by fib_trie.c */ +extern void fib_trie_init(void); +extern struct fib_table *fib_trie_table(u32 id); static inline void fib_combine_itag(u32 *itag, struct fib_result *res) { -#ifdef CONFIG_NET_CLS_ROUTE +#ifdef CONFIG_IP_ROUTE_CLASSID #ifdef CONFIG_IP_MULTIPLE_TABLES u32 rtag; #endif diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index b7bbd6c28cfa..5d75feadf4f4 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -28,6 +28,80 @@ #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) #include <net/netfilter/nf_conntrack.h> #endif +#include <net/net_namespace.h> /* Netw namespace */ + +/* + * Generic access of ipvs struct + */ +static inline struct netns_ipvs *net_ipvs(struct net* net) +{ + return net->ipvs; +} +/* + * Get net ptr from skb in traffic cases + * use skb_sknet when call is from userland (ioctl or netlink) + */ +static inline struct net *skb_net(const struct sk_buff *skb) +{ +#ifdef CONFIG_NET_NS +#ifdef CONFIG_IP_VS_DEBUG + /* + * This is used for debug only. + * Start with the most likely hit + * End with BUG + */ + if (likely(skb->dev && skb->dev->nd_net)) + return dev_net(skb->dev); + if (skb_dst(skb)->dev) + return dev_net(skb_dst(skb)->dev); + WARN(skb->sk, "Maybe skb_sknet should be used in %s() at line:%d\n", + __func__, __LINE__); + if (likely(skb->sk && skb->sk->sk_net)) + return sock_net(skb->sk); + pr_err("There is no net ptr to find in the skb in %s() line:%d\n", + __func__, __LINE__); + BUG(); +#else + return dev_net(skb->dev ? : skb_dst(skb)->dev); +#endif +#else + return &init_net; +#endif +} + +static inline struct net *skb_sknet(const struct sk_buff *skb) +{ +#ifdef CONFIG_NET_NS +#ifdef CONFIG_IP_VS_DEBUG + /* Start with the most likely hit */ + if (likely(skb->sk && skb->sk->sk_net)) + return sock_net(skb->sk); + WARN(skb->dev, "Maybe skb_net should be used instead in %s() line:%d\n", + __func__, __LINE__); + if (likely(skb->dev && skb->dev->nd_net)) + return dev_net(skb->dev); + pr_err("There is no net ptr to find in the skb in %s() line:%d\n", + __func__, __LINE__); + BUG(); +#else + return sock_net(skb->sk); +#endif +#else + return &init_net; +#endif +} +/* + * This one needed for single_open_net since net is stored directly in + * private not as a struct i.e. seq_file_net cant be used. + */ +static inline struct net *seq_file_single_net(struct seq_file *seq) +{ +#ifdef CONFIG_NET_NS + return (struct net *)seq->private; +#else + return &init_net; +#endif +} /* Connections' size value needed by ip_vs_ctl.c */ extern int ip_vs_conn_tab_size; @@ -258,6 +332,23 @@ struct ip_vs_seq { before last resized pkt */ }; +/* + * counters per cpu + */ +struct ip_vs_counters { + __u32 conns; /* connections scheduled */ + __u32 inpkts; /* incoming packets */ + __u32 outpkts; /* outgoing packets */ + __u64 inbytes; /* incoming bytes */ + __u64 outbytes; /* outgoing bytes */ +}; +/* + * Stats per cpu + */ +struct ip_vs_cpu_stats { + struct ip_vs_counters ustats; + struct u64_stats_sync syncp; +}; /* * IPVS statistics objects @@ -279,17 +370,34 @@ struct ip_vs_estimator { }; struct ip_vs_stats { - struct ip_vs_stats_user ustats; /* statistics */ + struct ip_vs_stats_user ustats; /* statistics */ struct ip_vs_estimator est; /* estimator */ - - spinlock_t lock; /* spin lock */ + struct ip_vs_cpu_stats *cpustats; /* per cpu counters */ + spinlock_t lock; /* spin lock */ }; +/* + * Helper Macros for per cpu + * ipvs->tot_stats->ustats.count + */ +#define IPVS_STAT_INC(ipvs, count) \ + __this_cpu_inc((ipvs)->ustats->count) + +#define IPVS_STAT_ADD(ipvs, count, value) \ + do {\ + write_seqcount_begin(per_cpu_ptr((ipvs)->ustats_seq, \ + raw_smp_processor_id())); \ + __this_cpu_add((ipvs)->ustats->count, value); \ + write_seqcount_end(per_cpu_ptr((ipvs)->ustats_seq, \ + raw_smp_processor_id())); \ + } while (0) + struct dst_entry; struct iphdr; struct ip_vs_conn; struct ip_vs_app; struct sk_buff; +struct ip_vs_proto_data; struct ip_vs_protocol { struct ip_vs_protocol *next; @@ -297,21 +405,22 @@ struct ip_vs_protocol { u16 protocol; u16 num_states; int dont_defrag; - atomic_t appcnt; /* counter of proto app incs */ - int *timeout_table; /* protocol timeout table */ void (*init)(struct ip_vs_protocol *pp); void (*exit)(struct ip_vs_protocol *pp); + void (*init_netns)(struct net *net, struct ip_vs_proto_data *pd); + + void (*exit_netns)(struct net *net, struct ip_vs_proto_data *pd); + int (*conn_schedule)(int af, struct sk_buff *skb, - struct ip_vs_protocol *pp, + struct ip_vs_proto_data *pd, int *verdict, struct ip_vs_conn **cpp); struct ip_vs_conn * (*conn_in_get)(int af, const struct sk_buff *skb, - struct ip_vs_protocol *pp, const struct ip_vs_iphdr *iph, unsigned int proto_off, int inverse); @@ -319,7 +428,6 @@ struct ip_vs_protocol { struct ip_vs_conn * (*conn_out_get)(int af, const struct sk_buff *skb, - struct ip_vs_protocol *pp, const struct ip_vs_iphdr *iph, unsigned int proto_off, int inverse); @@ -337,11 +445,11 @@ struct ip_vs_protocol { int (*state_transition)(struct ip_vs_conn *cp, int direction, const struct sk_buff *skb, - struct ip_vs_protocol *pp); + struct ip_vs_proto_data *pd); - int (*register_app)(struct ip_vs_app *inc); + int (*register_app)(struct net *net, struct ip_vs_app *inc); - void (*unregister_app)(struct ip_vs_app *inc); + void (*unregister_app)(struct net *net, struct ip_vs_app *inc); int (*app_conn_bind)(struct ip_vs_conn *cp); @@ -350,14 +458,26 @@ struct ip_vs_protocol { int offset, const char *msg); - void (*timeout_change)(struct ip_vs_protocol *pp, int flags); + void (*timeout_change)(struct ip_vs_proto_data *pd, int flags); +}; - int (*set_state_timeout)(struct ip_vs_protocol *pp, char *sname, int to); +/* + * protocol data per netns + */ +struct ip_vs_proto_data { + struct ip_vs_proto_data *next; + struct ip_vs_protocol *pp; + int *timeout_table; /* protocol timeout table */ + atomic_t appcnt; /* counter of proto app incs. */ + struct tcp_states_t *tcp_state_table; }; -extern struct ip_vs_protocol * ip_vs_proto_get(unsigned short proto); +extern struct ip_vs_protocol *ip_vs_proto_get(unsigned short proto); +extern struct ip_vs_proto_data *ip_vs_proto_data_get(struct net *net, + unsigned short proto); struct ip_vs_conn_param { + struct net *net; const union nf_inet_addr *caddr; const union nf_inet_addr *vaddr; __be16 cport; @@ -375,16 +495,19 @@ struct ip_vs_conn_param { */ struct ip_vs_conn { struct list_head c_list; /* hashed list heads */ - +#ifdef CONFIG_NET_NS + struct net *net; /* Name space */ +#endif /* Protocol, addresses and port numbers */ - u16 af; /* address family */ - union nf_inet_addr caddr; /* client address */ - union nf_inet_addr vaddr; /* virtual address */ - union nf_inet_addr daddr; /* destination address */ - volatile __u32 flags; /* status flags */ - __be16 cport; - __be16 vport; - __be16 dport; + u16 af; /* address family */ + __be16 cport; + __be16 vport; + __be16 dport; + __u32 fwmark; /* Fire wall mark from skb */ + union nf_inet_addr caddr; /* client address */ + union nf_inet_addr vaddr; /* virtual address */ + union nf_inet_addr daddr; /* destination address */ + volatile __u32 flags; /* status flags */ __u16 protocol; /* Which protocol (TCP/UDP) */ /* counter and timer */ @@ -422,10 +545,38 @@ struct ip_vs_conn { struct ip_vs_seq in_seq; /* incoming seq. struct */ struct ip_vs_seq out_seq; /* outgoing seq. struct */ + const struct ip_vs_pe *pe; char *pe_data; __u8 pe_data_len; }; +/* + * To save some memory in conn table when name space is disabled. + */ +static inline struct net *ip_vs_conn_net(const struct ip_vs_conn *cp) +{ +#ifdef CONFIG_NET_NS + return cp->net; +#else + return &init_net; +#endif +} +static inline void ip_vs_conn_net_set(struct ip_vs_conn *cp, struct net *net) +{ +#ifdef CONFIG_NET_NS + cp->net = net; +#endif +} + +static inline int ip_vs_conn_net_eq(const struct ip_vs_conn *cp, + struct net *net) +{ +#ifdef CONFIG_NET_NS + return cp->net == net; +#else + return 1; +#endif +} /* * Extended internal versions of struct ip_vs_service_user and @@ -485,6 +636,7 @@ struct ip_vs_service { unsigned flags; /* service status flags */ unsigned timeout; /* persistent timeout in ticks */ __be32 netmask; /* grouping granularity */ + struct net *net; struct list_head destinations; /* real server d-linked list */ __u32 num_dests; /* number of servers */ @@ -510,8 +662,8 @@ struct ip_vs_dest { struct list_head d_list; /* for table with all the dests */ u16 af; /* address family */ - union nf_inet_addr addr; /* IP address of the server */ __be16 port; /* port number of the server */ + union nf_inet_addr addr; /* IP address of the server */ volatile unsigned flags; /* dest status flags */ atomic_t conn_flags; /* flags to copy to conn */ atomic_t weight; /* server weight */ @@ -538,8 +690,8 @@ struct ip_vs_dest { /* for virtual service */ struct ip_vs_service *svc; /* service it belongs to */ __u16 protocol; /* which protocol (TCP/UDP) */ - union nf_inet_addr vaddr; /* virtual IP address */ __be16 vport; /* virtual port number */ + union nf_inet_addr vaddr; /* virtual IP address */ __u32 vfwmark; /* firewall mark of service */ }; @@ -674,13 +826,14 @@ enum { IP_VS_DIR_LAST, }; -static inline void ip_vs_conn_fill_param(int af, int protocol, +static inline void ip_vs_conn_fill_param(struct net *net, int af, int protocol, const union nf_inet_addr *caddr, __be16 cport, const union nf_inet_addr *vaddr, __be16 vport, struct ip_vs_conn_param *p) { + p->net = net; p->af = af; p->protocol = protocol; p->caddr = caddr; @@ -695,7 +848,6 @@ struct ip_vs_conn *ip_vs_conn_in_get(const struct ip_vs_conn_param *p); struct ip_vs_conn *ip_vs_ct_in_get(const struct ip_vs_conn_param *p); struct ip_vs_conn * ip_vs_conn_in_get_proto(int af, const struct sk_buff *skb, - struct ip_vs_protocol *pp, const struct ip_vs_iphdr *iph, unsigned int proto_off, int inverse); @@ -703,7 +855,6 @@ struct ip_vs_conn * ip_vs_conn_in_get_proto(int af, const struct sk_buff *skb, struct ip_vs_conn *ip_vs_conn_out_get(const struct ip_vs_conn_param *p); struct ip_vs_conn * ip_vs_conn_out_get_proto(int af, const struct sk_buff *skb, - struct ip_vs_protocol *pp, const struct ip_vs_iphdr *iph, unsigned int proto_off, int inverse); @@ -719,14 +870,14 @@ extern void ip_vs_conn_fill_cport(struct ip_vs_conn *cp, __be16 cport); struct ip_vs_conn *ip_vs_conn_new(const struct ip_vs_conn_param *p, const union nf_inet_addr *daddr, __be16 dport, unsigned flags, - struct ip_vs_dest *dest); + struct ip_vs_dest *dest, __u32 fwmark); extern void ip_vs_conn_expire_now(struct ip_vs_conn *cp); extern const char * ip_vs_state_name(__u16 proto, int state); -extern void ip_vs_tcp_conn_listen(struct ip_vs_conn *cp); +extern void ip_vs_tcp_conn_listen(struct net *net, struct ip_vs_conn *cp); extern int ip_vs_check_template(struct ip_vs_conn *ct); -extern void ip_vs_random_dropentry(void); +extern void ip_vs_random_dropentry(struct net *net); extern int ip_vs_conn_init(void); extern void ip_vs_conn_cleanup(void); @@ -796,12 +947,12 @@ ip_vs_control_add(struct ip_vs_conn *cp, struct ip_vs_conn *ctl_cp) * (from ip_vs_app.c) */ #define IP_VS_APP_MAX_PORTS 8 -extern int register_ip_vs_app(struct ip_vs_app *app); -extern void unregister_ip_vs_app(struct ip_vs_app *app); +extern int register_ip_vs_app(struct net *net, struct ip_vs_app *app); +extern void unregister_ip_vs_app(struct net *net, struct ip_vs_app *app); extern int ip_vs_bind_app(struct ip_vs_conn *cp, struct ip_vs_protocol *pp); extern void ip_vs_unbind_app(struct ip_vs_conn *cp); -extern int -register_ip_vs_app_inc(struct ip_vs_app *app, __u16 proto, __u16 port); +extern int register_ip_vs_app_inc(struct net *net, struct ip_vs_app *app, + __u16 proto, __u16 port); extern int ip_vs_app_inc_get(struct ip_vs_app *inc); extern void ip_vs_app_inc_put(struct ip_vs_app *inc); @@ -814,15 +965,27 @@ void ip_vs_bind_pe(struct ip_vs_service *svc, struct ip_vs_pe *pe); void ip_vs_unbind_pe(struct ip_vs_service *svc); int register_ip_vs_pe(struct ip_vs_pe *pe); int unregister_ip_vs_pe(struct ip_vs_pe *pe); -extern struct ip_vs_pe *ip_vs_pe_get(const char *name); -extern void ip_vs_pe_put(struct ip_vs_pe *pe); +struct ip_vs_pe *ip_vs_pe_getbyname(const char *name); +struct ip_vs_pe *__ip_vs_pe_getbyname(const char *pe_name); + +static inline void ip_vs_pe_get(const struct ip_vs_pe *pe) +{ + if (pe && pe->module) + __module_get(pe->module); +} + +static inline void ip_vs_pe_put(const struct ip_vs_pe *pe) +{ + if (pe && pe->module) + module_put(pe->module); +} /* * IPVS protocol functions (from ip_vs_proto.c) */ extern int ip_vs_protocol_init(void); extern void ip_vs_protocol_cleanup(void); -extern void ip_vs_protocol_timeout_change(int flags); +extern void ip_vs_protocol_timeout_change(struct netns_ipvs *ipvs, int flags); extern int *ip_vs_create_timeout_table(int *table, int size); extern int ip_vs_set_state_timeout(int *table, int num, const char *const *names, @@ -852,26 +1015,21 @@ extern struct ip_vs_scheduler *ip_vs_scheduler_get(const char *sched_name); extern void ip_vs_scheduler_put(struct ip_vs_scheduler *scheduler); extern struct ip_vs_conn * ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb, - struct ip_vs_protocol *pp, int *ignored); + struct ip_vs_proto_data *pd, int *ignored); extern int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb, - struct ip_vs_protocol *pp); + struct ip_vs_proto_data *pd); /* * IPVS control data and functions (from ip_vs_ctl.c) */ -extern int sysctl_ip_vs_cache_bypass; -extern int sysctl_ip_vs_expire_nodest_conn; -extern int sysctl_ip_vs_expire_quiescent_template; -extern int sysctl_ip_vs_sync_threshold[2]; -extern int sysctl_ip_vs_nat_icmp_send; -extern int sysctl_ip_vs_conntrack; -extern int sysctl_ip_vs_snat_reroute; extern struct ip_vs_stats ip_vs_stats; extern const struct ctl_path net_vs_ctl_path[]; +extern int sysctl_ip_vs_sync_ver; +extern void ip_vs_sync_switch_mode(struct net *net, int mode); extern struct ip_vs_service * -ip_vs_service_get(int af, __u32 fwmark, __u16 protocol, +ip_vs_service_get(struct net *net, int af, __u32 fwmark, __u16 protocol, const union nf_inet_addr *vaddr, __be16 vport); static inline void ip_vs_service_put(struct ip_vs_service *svc) @@ -880,7 +1038,7 @@ static inline void ip_vs_service_put(struct ip_vs_service *svc) } extern struct ip_vs_dest * -ip_vs_lookup_real_service(int af, __u16 protocol, +ip_vs_lookup_real_service(struct net *net, int af, __u16 protocol, const union nf_inet_addr *daddr, __be16 dport); extern int ip_vs_use_count_inc(void); @@ -888,8 +1046,9 @@ extern void ip_vs_use_count_dec(void); extern int ip_vs_control_init(void); extern void ip_vs_control_cleanup(void); extern struct ip_vs_dest * -ip_vs_find_dest(int af, const union nf_inet_addr *daddr, __be16 dport, - const union nf_inet_addr *vaddr, __be16 vport, __u16 protocol); +ip_vs_find_dest(struct net *net, int af, const union nf_inet_addr *daddr, + __be16 dport, const union nf_inet_addr *vaddr, __be16 vport, + __u16 protocol, __u32 fwmark); extern struct ip_vs_dest *ip_vs_try_bind_dest(struct ip_vs_conn *cp); @@ -897,14 +1056,12 @@ extern struct ip_vs_dest *ip_vs_try_bind_dest(struct ip_vs_conn *cp); * IPVS sync daemon data and function prototypes * (from ip_vs_sync.c) */ -extern volatile int ip_vs_sync_state; -extern volatile int ip_vs_master_syncid; -extern volatile int ip_vs_backup_syncid; -extern char ip_vs_master_mcast_ifn[IP_VS_IFNAME_MAXLEN]; -extern char ip_vs_backup_mcast_ifn[IP_VS_IFNAME_MAXLEN]; -extern int start_sync_thread(int state, char *mcast_ifn, __u8 syncid); -extern int stop_sync_thread(int state); -extern void ip_vs_sync_conn(struct ip_vs_conn *cp); +extern int start_sync_thread(struct net *net, int state, char *mcast_ifn, + __u8 syncid); +extern int stop_sync_thread(struct net *net, int state); +extern void ip_vs_sync_conn(struct net *net, struct ip_vs_conn *cp); +extern int ip_vs_sync_init(void); +extern void ip_vs_sync_cleanup(void); /* @@ -912,8 +1069,8 @@ extern void ip_vs_sync_conn(struct ip_vs_conn *cp); */ extern int ip_vs_estimator_init(void); extern void ip_vs_estimator_cleanup(void); -extern void ip_vs_new_estimator(struct ip_vs_stats *stats); -extern void ip_vs_kill_estimator(struct ip_vs_stats *stats); +extern void ip_vs_new_estimator(struct net *net, struct ip_vs_stats *stats); +extern void ip_vs_kill_estimator(struct net *net, struct ip_vs_stats *stats); extern void ip_vs_zero_estimator(struct ip_vs_stats *stats); /* @@ -952,14 +1109,14 @@ extern int ip_vs_icmp_xmit_v6 * we are loaded. Just set ip_vs_drop_rate to 'n' and * we start to drop 1/rate of the packets */ -extern int ip_vs_drop_rate; -extern int ip_vs_drop_counter; -static __inline__ int ip_vs_todrop(void) +static inline int ip_vs_todrop(struct netns_ipvs *ipvs) { - if (!ip_vs_drop_rate) return 0; - if (--ip_vs_drop_counter > 0) return 0; - ip_vs_drop_counter = ip_vs_drop_rate; + if (!ipvs->drop_rate) + return 0; + if (--ipvs->drop_counter > 0) + return 0; + ipvs->drop_counter = ipvs->drop_rate; return 1; } @@ -1047,9 +1204,9 @@ static inline void ip_vs_notrack(struct sk_buff *skb) * Netfilter connection tracking * (from ip_vs_nfct.c) */ -static inline int ip_vs_conntrack_enabled(void) +static inline int ip_vs_conntrack_enabled(struct netns_ipvs *ipvs) { - return sysctl_ip_vs_conntrack; + return ipvs->sysctl_conntrack; } extern void ip_vs_update_conntrack(struct sk_buff *skb, struct ip_vs_conn *cp, @@ -1062,7 +1219,7 @@ extern void ip_vs_conn_drop_conntrack(struct ip_vs_conn *cp); #else -static inline int ip_vs_conntrack_enabled(void) +static inline int ip_vs_conntrack_enabled(struct netns_ipvs *ipvs) { return 0; } diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 62c0ce2d1dc8..d6b0045788ce 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1147,6 +1147,17 @@ enum ieee80211_hw_flags { * @napi_weight: weight used for NAPI polling. You must specify an * appropriate value here if a napi_poll operation is provided * by your driver. + + * @max_rx_aggregation_subframes: maximum buffer size (number of + * sub-frames) to be used for A-MPDU block ack receiver + * aggregation. + * This is only relevant if the device has restrictions on the + * number of subframes, if it relies on mac80211 to do reordering + * it shouldn't be set. + * + * @max_tx_aggregation_subframes: maximum number of subframes in an + * aggregate an HT driver will transmit, used by the peer as a + * hint to size its reorder buffer. */ struct ieee80211_hw { struct ieee80211_conf conf; @@ -1165,6 +1176,8 @@ struct ieee80211_hw { u8 max_rates; u8 max_report_rates; u8 max_rate_tries; + u8 max_rx_aggregation_subframes; + u8 max_tx_aggregation_subframes; }; /** @@ -1723,6 +1736,10 @@ enum ieee80211_ampdu_mlme_action { * ieee80211_ampdu_mlme_action. Starting sequence number (@ssn) * is the first frame we expect to perform the action on. Notice * that TX/RX_STOP can pass NULL for this parameter. + * The @buf_size parameter is only valid when the action is set to + * %IEEE80211_AMPDU_TX_OPERATIONAL and indicates the peer's reorder + * buffer size (number of subframes) for this session -- aggregates + * containing more subframes than this may not be transmitted to the peer. * Returns a negative error code on failure. * The callback can sleep. * @@ -1825,7 +1842,8 @@ struct ieee80211_ops { int (*ampdu_action)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, enum ieee80211_ampdu_mlme_action action, - struct ieee80211_sta *sta, u16 tid, u16 *ssn); + struct ieee80211_sta *sta, u16 tid, u16 *ssn, + u8 buf_size); int (*get_survey)(struct ieee80211_hw *hw, int idx, struct survey_info *survey); void (*rfkill_poll)(struct ieee80211_hw *hw); diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index 1bf812b21fb7..b3b4a34cb2cc 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -20,6 +20,7 @@ #include <net/netns/conntrack.h> #endif #include <net/netns/xfrm.h> +#include <net/netns/ip_vs.h> struct proc_dir_entry; struct net_device; @@ -94,6 +95,7 @@ struct net { #ifdef CONFIG_XFRM struct netns_xfrm xfrm; #endif + struct netns_ipvs *ipvs; }; diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index d85cff10e169..d0d13378991e 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -50,11 +50,24 @@ union nf_conntrack_expect_proto { /* per conntrack: application helper private data */ union nf_conntrack_help { /* insert conntrack helper private data (master) here */ +#if defined(CONFIG_NF_CONNTRACK_FTP) || defined(CONFIG_NF_CONNTRACK_FTP_MODULE) struct nf_ct_ftp_master ct_ftp_info; +#endif +#if defined(CONFIG_NF_CONNTRACK_PPTP) || \ + defined(CONFIG_NF_CONNTRACK_PPTP_MODULE) struct nf_ct_pptp_master ct_pptp_info; +#endif +#if defined(CONFIG_NF_CONNTRACK_H323) || \ + defined(CONFIG_NF_CONNTRACK_H323_MODULE) struct nf_ct_h323_master ct_h323_info; +#endif +#if defined(CONFIG_NF_CONNTRACK_SANE) || \ + defined(CONFIG_NF_CONNTRACK_SANE_MODULE) struct nf_ct_sane_master ct_sane_info; +#endif +#if defined(CONFIG_NF_CONNTRACK_SIP) || defined(CONFIG_NF_CONNTRACK_SIP_MODULE) struct nf_ct_sip_master ct_sip_info; +#endif }; #include <linux/types.h> @@ -116,14 +129,14 @@ struct nf_conn { u_int32_t secmark; #endif - /* Storage reserved for other modules: */ - union nf_conntrack_proto proto; - /* Extensions */ struct nf_ct_ext *ext; #ifdef CONFIG_NET_NS struct net *ct_net; #endif + + /* Storage reserved for other modules, must be the last member */ + union nf_conntrack_proto proto; }; static inline struct nf_conn * @@ -189,9 +202,9 @@ extern void nf_ct_l3proto_module_put(unsigned short l3proto); * Allocate a hashtable of hlist_head (if nulls == 0), * or hlist_nulls_head (if nulls == 1) */ -extern void *nf_ct_alloc_hashtable(unsigned int *sizep, int *vmalloced, int nulls); +extern void *nf_ct_alloc_hashtable(unsigned int *sizep, int nulls); -extern void nf_ct_free_hashtable(void *hash, int vmalloced, unsigned int size); +extern void nf_ct_free_hashtable(void *hash, unsigned int size); extern struct nf_conntrack_tuple_hash * __nf_conntrack_find(struct net *net, u16 zone, diff --git a/include/net/netfilter/nf_conntrack_ecache.h b/include/net/netfilter/nf_conntrack_ecache.h index 349cefedc9f3..4283508b3e18 100644 --- a/include/net/netfilter/nf_conntrack_ecache.h +++ b/include/net/netfilter/nf_conntrack_ecache.h @@ -23,12 +23,17 @@ struct nf_conntrack_ecache { static inline struct nf_conntrack_ecache * nf_ct_ecache_find(const struct nf_conn *ct) { +#ifdef CONFIG_NF_CONNTRACK_EVENTS return nf_ct_ext_find(ct, NF_CT_EXT_ECACHE); +#else + return NULL; +#endif } static inline struct nf_conntrack_ecache * nf_ct_ecache_ext_add(struct nf_conn *ct, u16 ctmask, u16 expmask, gfp_t gfp) { +#ifdef CONFIG_NF_CONNTRACK_EVENTS struct net *net = nf_ct_net(ct); struct nf_conntrack_ecache *e; @@ -45,6 +50,9 @@ nf_ct_ecache_ext_add(struct nf_conn *ct, u16 ctmask, u16 expmask, gfp_t gfp) e->expmask = expmask; } return e; +#else + return NULL; +#endif }; #ifdef CONFIG_NF_CONNTRACK_EVENTS @@ -59,7 +67,7 @@ struct nf_ct_event_notifier { int (*fcn)(unsigned int events, struct nf_ct_event *item); }; -extern struct nf_ct_event_notifier *nf_conntrack_event_cb; +extern struct nf_ct_event_notifier __rcu *nf_conntrack_event_cb; extern int nf_conntrack_register_notifier(struct nf_ct_event_notifier *nb); extern void nf_conntrack_unregister_notifier(struct nf_ct_event_notifier *nb); @@ -156,7 +164,7 @@ struct nf_exp_event_notifier { int (*fcn)(unsigned int events, struct nf_exp_event *item); }; -extern struct nf_exp_event_notifier *nf_expect_event_cb; +extern struct nf_exp_event_notifier __rcu *nf_expect_event_cb; extern int nf_ct_expect_register_notifier(struct nf_exp_event_notifier *nb); extern void nf_ct_expect_unregister_notifier(struct nf_exp_event_notifier *nb); diff --git a/include/net/netfilter/nf_conntrack_extend.h b/include/net/netfilter/nf_conntrack_extend.h index 0772d296dfdb..2dcf31703acb 100644 --- a/include/net/netfilter/nf_conntrack_extend.h +++ b/include/net/netfilter/nf_conntrack_extend.h @@ -7,10 +7,19 @@ enum nf_ct_ext_id { NF_CT_EXT_HELPER, +#if defined(CONFIG_NF_NAT) || defined(CONFIG_NF_NAT_MODULE) NF_CT_EXT_NAT, +#endif NF_CT_EXT_ACCT, +#ifdef CONFIG_NF_CONNTRACK_EVENTS NF_CT_EXT_ECACHE, +#endif +#ifdef CONFIG_NF_CONNTRACK_ZONES NF_CT_EXT_ZONE, +#endif +#ifdef CONFIG_NF_CONNTRACK_TIMESTAMP + NF_CT_EXT_TSTAMP, +#endif NF_CT_EXT_NUM, }; @@ -19,6 +28,7 @@ enum nf_ct_ext_id { #define NF_CT_EXT_ACCT_TYPE struct nf_conn_counter #define NF_CT_EXT_ECACHE_TYPE struct nf_conntrack_ecache #define NF_CT_EXT_ZONE_TYPE struct nf_conntrack_zone +#define NF_CT_EXT_TSTAMP_TYPE struct nf_conn_tstamp /* Extensions: optional stuff which isn't permanently in struct. */ struct nf_ct_ext { diff --git a/include/net/netfilter/nf_conntrack_helper.h b/include/net/netfilter/nf_conntrack_helper.h index 32c305dbdab6..f1c1311adc2c 100644 --- a/include/net/netfilter/nf_conntrack_helper.h +++ b/include/net/netfilter/nf_conntrack_helper.h @@ -63,4 +63,10 @@ static inline struct nf_conn_help *nfct_help(const struct nf_conn *ct) extern int nf_conntrack_helper_init(void); extern void nf_conntrack_helper_fini(void); +extern int nf_conntrack_broadcast_help(struct sk_buff *skb, + unsigned int protoff, + struct nf_conn *ct, + enum ip_conntrack_info ctinfo, + unsigned int timeout); + #endif /*_NF_CONNTRACK_HELPER_H*/ diff --git a/include/net/netfilter/nf_conntrack_l3proto.h b/include/net/netfilter/nf_conntrack_l3proto.h index a7547611e8f1..e8010f445ae1 100644 --- a/include/net/netfilter/nf_conntrack_l3proto.h +++ b/include/net/netfilter/nf_conntrack_l3proto.h @@ -73,7 +73,7 @@ struct nf_conntrack_l3proto { struct module *me; }; -extern struct nf_conntrack_l3proto *nf_ct_l3protos[AF_MAX]; +extern struct nf_conntrack_l3proto __rcu *nf_ct_l3protos[AF_MAX]; /* Protocol registration. */ extern int nf_conntrack_l3proto_register(struct nf_conntrack_l3proto *proto); diff --git a/include/net/netfilter/nf_conntrack_timestamp.h b/include/net/netfilter/nf_conntrack_timestamp.h new file mode 100644 index 000000000000..fc9c82b1f06b --- /dev/null +++ b/include/net/netfilter/nf_conntrack_timestamp.h @@ -0,0 +1,65 @@ +#ifndef _NF_CONNTRACK_TSTAMP_H +#define _NF_CONNTRACK_TSTAMP_H + +#include <net/net_namespace.h> +#include <linux/netfilter/nf_conntrack_common.h> +#include <linux/netfilter/nf_conntrack_tuple_common.h> +#include <net/netfilter/nf_conntrack.h> +#include <net/netfilter/nf_conntrack_extend.h> + +struct nf_conn_tstamp { + u_int64_t start; + u_int64_t stop; +}; + +static inline +struct nf_conn_tstamp *nf_conn_tstamp_find(const struct nf_conn *ct) +{ +#ifdef CONFIG_NF_CONNTRACK_TIMESTAMP + return nf_ct_ext_find(ct, NF_CT_EXT_TSTAMP); +#else + return NULL; +#endif +} + +static inline +struct nf_conn_tstamp *nf_ct_tstamp_ext_add(struct nf_conn *ct, gfp_t gfp) +{ +#ifdef CONFIG_NF_CONNTRACK_TIMESTAMP + struct net *net = nf_ct_net(ct); + + if (!net->ct.sysctl_tstamp) + return NULL; + + return nf_ct_ext_add(ct, NF_CT_EXT_TSTAMP, gfp); +#else + return NULL; +#endif +}; + +static inline bool nf_ct_tstamp_enabled(struct net *net) +{ + return net->ct.sysctl_tstamp != 0; +} + +static inline void nf_ct_set_tstamp(struct net *net, bool enable) +{ + net->ct.sysctl_tstamp = enable; +} + +#ifdef CONFIG_NF_CONNTRACK_TIMESTAMP +extern int nf_conntrack_tstamp_init(struct net *net); +extern void nf_conntrack_tstamp_fini(struct net *net); +#else +static inline int nf_conntrack_tstamp_init(struct net *net) +{ + return 0; +} + +static inline void nf_conntrack_tstamp_fini(struct net *net) +{ + return; +} +#endif /* CONFIG_NF_CONNTRACK_TIMESTAMP */ + +#endif /* _NF_CONNTRACK_TSTAMP_H */ diff --git a/include/net/netfilter/nf_nat.h b/include/net/netfilter/nf_nat.h index f5f09f032a90..aff80b190c12 100644 --- a/include/net/netfilter/nf_nat.h +++ b/include/net/netfilter/nf_nat.h @@ -56,7 +56,9 @@ struct nf_nat_multi_range_compat { /* per conntrack: nat application helper private data */ union nf_conntrack_nat_help { /* insert nat helper private data here */ +#if defined(CONFIG_NF_NAT_PPTP) || defined(CONFIG_NF_NAT_PPTP_MODULE) struct nf_nat_pptp nat_pptp_info; +#endif }; struct nf_conn; @@ -84,7 +86,11 @@ extern int nf_nat_used_tuple(const struct nf_conntrack_tuple *tuple, static inline struct nf_conn_nat *nfct_nat(const struct nf_conn *ct) { +#if defined(CONFIG_NF_NAT) || defined(CONFIG_NF_NAT_MODULE) return nf_ct_ext_find(ct, NF_CT_EXT_NAT); +#else + return NULL; +#endif } #else /* !__KERNEL__: iptables wants this to compile. */ diff --git a/include/net/netfilter/nf_nat_core.h b/include/net/netfilter/nf_nat_core.h index 33602ab66190..3dc7b98effeb 100644 --- a/include/net/netfilter/nf_nat_core.h +++ b/include/net/netfilter/nf_nat_core.h @@ -21,9 +21,9 @@ static inline int nf_nat_initialized(struct nf_conn *ct, enum nf_nat_manip_type manip) { if (manip == IP_NAT_MANIP_SRC) - return test_bit(IPS_SRC_NAT_DONE_BIT, &ct->status); + return ct->status & IPS_SRC_NAT_DONE; else - return test_bit(IPS_DST_NAT_DONE_BIT, &ct->status); + return ct->status & IPS_DST_NAT_DONE; } struct nlattr; diff --git a/include/net/netlink.h b/include/net/netlink.h index 373f1a900cf4..8a3906a08f5f 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -856,18 +856,27 @@ static inline int nla_put_msecs(struct sk_buff *skb, int attrtype, #define NLA_PUT_BE16(skb, attrtype, value) \ NLA_PUT_TYPE(skb, __be16, attrtype, value) +#define NLA_PUT_NET16(skb, attrtype, value) \ + NLA_PUT_BE16(skb, attrtype | NLA_F_NET_BYTEORDER, value) + #define NLA_PUT_U32(skb, attrtype, value) \ NLA_PUT_TYPE(skb, u32, attrtype, value) #define NLA_PUT_BE32(skb, attrtype, value) \ NLA_PUT_TYPE(skb, __be32, attrtype, value) +#define NLA_PUT_NET32(skb, attrtype, value) \ + NLA_PUT_BE32(skb, attrtype | NLA_F_NET_BYTEORDER, value) + #define NLA_PUT_U64(skb, attrtype, value) \ NLA_PUT_TYPE(skb, u64, attrtype, value) #define NLA_PUT_BE64(skb, attrtype, value) \ NLA_PUT_TYPE(skb, __be64, attrtype, value) +#define NLA_PUT_NET64(skb, attrtype, value) \ + NLA_PUT_BE64(skb, attrtype | NLA_F_NET_BYTEORDER, value) + #define NLA_PUT_STRING(skb, attrtype, value) \ NLA_PUT(skb, attrtype, strlen(value) + 1, value) diff --git a/include/net/netns/conntrack.h b/include/net/netns/conntrack.h index d4958d4c6574..341eb089349e 100644 --- a/include/net/netns/conntrack.h +++ b/include/net/netns/conntrack.h @@ -21,15 +21,15 @@ struct netns_ct { int sysctl_events; unsigned int sysctl_events_retry_timeout; int sysctl_acct; + int sysctl_tstamp; int sysctl_checksum; unsigned int sysctl_log_invalid; /* Log invalid packets */ #ifdef CONFIG_SYSCTL struct ctl_table_header *sysctl_header; struct ctl_table_header *acct_sysctl_header; + struct ctl_table_header *tstamp_sysctl_header; struct ctl_table_header *event_sysctl_header; #endif - int hash_vmalloc; - int expect_vmalloc; char *slabname; }; #endif diff --git a/include/net/netns/ip_vs.h b/include/net/netns/ip_vs.h new file mode 100644 index 000000000000..259ebac904bf --- /dev/null +++ b/include/net/netns/ip_vs.h @@ -0,0 +1,143 @@ +/* + * IP Virtual Server + * Data structure for network namspace + * + */ + +#ifndef IP_VS_H_ +#define IP_VS_H_ + +#include <linux/list.h> +#include <linux/mutex.h> +#include <linux/list_nulls.h> +#include <linux/ip_vs.h> +#include <asm/atomic.h> +#include <linux/in.h> + +struct ip_vs_stats; +struct ip_vs_sync_buff; +struct ctl_table_header; + +struct netns_ipvs { + int gen; /* Generation */ + /* + * Hash table: for real service lookups + */ + #define IP_VS_RTAB_BITS 4 + #define IP_VS_RTAB_SIZE (1 << IP_VS_RTAB_BITS) + #define IP_VS_RTAB_MASK (IP_VS_RTAB_SIZE - 1) + + struct list_head rs_table[IP_VS_RTAB_SIZE]; + /* ip_vs_app */ + struct list_head app_list; + struct mutex app_mutex; + struct lock_class_key app_key; /* mutex debuging */ + + /* ip_vs_proto */ + #define IP_VS_PROTO_TAB_SIZE 32 /* must be power of 2 */ + struct ip_vs_proto_data *proto_data_table[IP_VS_PROTO_TAB_SIZE]; + /* ip_vs_proto_tcp */ +#ifdef CONFIG_IP_VS_PROTO_TCP + #define TCP_APP_TAB_BITS 4 + #define TCP_APP_TAB_SIZE (1 << TCP_APP_TAB_BITS) + #define TCP_APP_TAB_MASK (TCP_APP_TAB_SIZE - 1) + struct list_head tcp_apps[TCP_APP_TAB_SIZE]; + spinlock_t tcp_app_lock; +#endif + /* ip_vs_proto_udp */ +#ifdef CONFIG_IP_VS_PROTO_UDP + #define UDP_APP_TAB_BITS 4 + #define UDP_APP_TAB_SIZE (1 << UDP_APP_TAB_BITS) + #define UDP_APP_TAB_MASK (UDP_APP_TAB_SIZE - 1) + struct list_head udp_apps[UDP_APP_TAB_SIZE]; + spinlock_t udp_app_lock; +#endif + /* ip_vs_proto_sctp */ +#ifdef CONFIG_IP_VS_PROTO_SCTP + #define SCTP_APP_TAB_BITS 4 + #define SCTP_APP_TAB_SIZE (1 << SCTP_APP_TAB_BITS) + #define SCTP_APP_TAB_MASK (SCTP_APP_TAB_SIZE - 1) + /* Hash table for SCTP application incarnations */ + struct list_head sctp_apps[SCTP_APP_TAB_SIZE]; + spinlock_t sctp_app_lock; +#endif + /* ip_vs_conn */ + atomic_t conn_count; /* connection counter */ + + /* ip_vs_ctl */ + struct ip_vs_stats *tot_stats; /* Statistics & est. */ + struct ip_vs_cpu_stats __percpu *cpustats; /* Stats per cpu */ + seqcount_t *ustats_seq; /* u64 read retry */ + + int num_services; /* no of virtual services */ + /* 1/rate drop and drop-entry variables */ + struct delayed_work defense_work; /* Work handler */ + int drop_rate; + int drop_counter; + atomic_t dropentry; + /* locks in ctl.c */ + spinlock_t dropentry_lock; /* drop entry handling */ + spinlock_t droppacket_lock; /* drop packet handling */ + spinlock_t securetcp_lock; /* state and timeout tables */ + rwlock_t rs_lock; /* real services table */ + /* semaphore for IPVS sockopts. And, [gs]etsockopt may sleep. */ + struct lock_class_key ctl_key; /* ctl_mutex debuging */ + /* Trash for destinations */ + struct list_head dest_trash; + /* Service counters */ + atomic_t ftpsvc_counter; + atomic_t nullsvc_counter; + + /* sys-ctl struct */ + struct ctl_table_header *sysctl_hdr; + struct ctl_table *sysctl_tbl; + /* sysctl variables */ + int sysctl_amemthresh; + int sysctl_am_droprate; + int sysctl_drop_entry; + int sysctl_drop_packet; + int sysctl_secure_tcp; +#ifdef CONFIG_IP_VS_NFCT + int sysctl_conntrack; +#endif + int sysctl_snat_reroute; + int sysctl_sync_ver; + int sysctl_cache_bypass; + int sysctl_expire_nodest_conn; + int sysctl_expire_quiescent_template; + int sysctl_sync_threshold[2]; + int sysctl_nat_icmp_send; + + /* ip_vs_lblc */ + int sysctl_lblc_expiration; + struct ctl_table_header *lblc_ctl_header; + struct ctl_table *lblc_ctl_table; + /* ip_vs_lblcr */ + int sysctl_lblcr_expiration; + struct ctl_table_header *lblcr_ctl_header; + struct ctl_table *lblcr_ctl_table; + /* ip_vs_est */ + struct list_head est_list; /* estimator list */ + spinlock_t est_lock; + struct timer_list est_timer; /* Estimation timer */ + /* ip_vs_sync */ + struct list_head sync_queue; + spinlock_t sync_lock; + struct ip_vs_sync_buff *sync_buff; + spinlock_t sync_buff_lock; + struct sockaddr_in sync_mcast_addr; + struct task_struct *master_thread; + struct task_struct *backup_thread; + int send_mesg_maxlen; + int recv_mesg_maxlen; + volatile int sync_state; + volatile int master_syncid; + volatile int backup_syncid; + /* multicast interface name */ + char master_mcast_ifn[IP_VS_IFNAME_MAXLEN]; + char backup_mcast_ifn[IP_VS_IFNAME_MAXLEN]; + /* net name space ptr */ + struct net *net; /* Needed by timer routines */ +}; + +#endif /* IP_VS_H_ */ diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index d68c3f121774..e2e2ef57eca2 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -43,7 +43,6 @@ struct netns_ipv4 { struct xt_table *nat_table; struct hlist_head *nat_bysource; unsigned int nat_htable_size; - int nat_vmalloced; #endif int sysctl_icmp_echo_ignore_all; diff --git a/include/net/protocol.h b/include/net/protocol.h index dc07495bce4c..6f7eb800974a 100644 --- a/include/net/protocol.h +++ b/include/net/protocol.h @@ -38,7 +38,7 @@ struct net_protocol { void (*err_handler)(struct sk_buff *skb, u32 info); int (*gso_send_check)(struct sk_buff *skb); struct sk_buff *(*gso_segment)(struct sk_buff *skb, - int features); + u32 features); struct sk_buff **(*gro_receive)(struct sk_buff **head, struct sk_buff *skb); int (*gro_complete)(struct sk_buff *skb); @@ -57,7 +57,7 @@ struct inet6_protocol { int (*gso_send_check)(struct sk_buff *skb); struct sk_buff *(*gso_segment)(struct sk_buff *skb, - int features); + u32 features); struct sk_buff **(*gro_receive)(struct sk_buff **head, struct sk_buff *skb); int (*gro_complete)(struct sk_buff *skb); diff --git a/include/net/route.h b/include/net/route.h index 93e10c453f6b..e5864658dc76 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -49,6 +49,7 @@ struct fib_nh; struct inet_peer; +struct fib_info; struct rtable { struct dst_entry dst; @@ -69,6 +70,7 @@ struct rtable { /* Miscellaneous cached information */ __be32 rt_spec_dst; /* RFC1122 specific destination */ struct inet_peer *peer; /* long-living peer info */ + struct fib_info *fi; /* for client ref to shared metrics */ }; static inline bool rt_is_input_route(struct rtable *rt) @@ -180,6 +182,8 @@ static inline int ip_route_connect(struct rtable **rp, __be32 dst, if (inet_sk(sk)->transparent) fl.flags |= FLOWI_FLAG_ANYSRC; + if (protocol == IPPROTO_TCP) + fl.flags |= FLOWI_FLAG_PRECOW_METRICS; if (!dst || !src) { err = __ip_route_output_key(net, rp, &fl); @@ -207,6 +211,8 @@ static inline int ip_route_newports(struct rtable **rp, u8 protocol, fl.proto = protocol; if (inet_sk(sk)->transparent) fl.flags |= FLOWI_FLAG_ANYSRC; + if (protocol == IPPROTO_TCP) + fl.flags |= FLOWI_FLAG_PRECOW_METRICS; ip_rt_put(*rp); *rp = NULL; security_sk_classify_flow(sk, &fl); diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 160a407c1963..16626a04cb03 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -31,10 +31,12 @@ enum qdisc_state_t { * following bits are only changed while qdisc lock is held */ enum qdisc___state_t { - __QDISC___STATE_RUNNING, + __QDISC___STATE_RUNNING = 1, + __QDISC___STATE_THROTTLED = 2, }; struct qdisc_size_table { + struct rcu_head rcu; struct list_head list; struct tc_sizespec szopts; int refcnt; @@ -46,14 +48,13 @@ struct Qdisc { struct sk_buff * (*dequeue)(struct Qdisc *dev); unsigned flags; #define TCQ_F_BUILTIN 1 -#define TCQ_F_THROTTLED 2 -#define TCQ_F_INGRESS 4 -#define TCQ_F_CAN_BYPASS 8 -#define TCQ_F_MQROOT 16 +#define TCQ_F_INGRESS 2 +#define TCQ_F_CAN_BYPASS 4 +#define TCQ_F_MQROOT 8 #define TCQ_F_WARN_NONWC (1 << 16) int padded; struct Qdisc_ops *ops; - struct qdisc_size_table *stab; + struct qdisc_size_table __rcu *stab; struct list_head list; u32 handle; u32 parent; @@ -78,25 +79,43 @@ struct Qdisc { unsigned long state; struct sk_buff_head q; struct gnet_stats_basic_packed bstats; - unsigned long __state; + unsigned int __state; struct gnet_stats_queue qstats; struct rcu_head rcu_head; spinlock_t busylock; }; -static inline bool qdisc_is_running(struct Qdisc *qdisc) +static inline bool qdisc_is_running(const struct Qdisc *qdisc) { - return test_bit(__QDISC___STATE_RUNNING, &qdisc->__state); + return (qdisc->__state & __QDISC___STATE_RUNNING) ? true : false; } static inline bool qdisc_run_begin(struct Qdisc *qdisc) { - return !__test_and_set_bit(__QDISC___STATE_RUNNING, &qdisc->__state); + if (qdisc_is_running(qdisc)) + return false; + qdisc->__state |= __QDISC___STATE_RUNNING; + return true; } static inline void qdisc_run_end(struct Qdisc *qdisc) { - __clear_bit(__QDISC___STATE_RUNNING, &qdisc->__state); + qdisc->__state &= ~__QDISC___STATE_RUNNING; +} + +static inline bool qdisc_is_throttled(const struct Qdisc *qdisc) +{ + return (qdisc->__state & __QDISC___STATE_THROTTLED) ? true : false; +} + +static inline void qdisc_throttled(struct Qdisc *qdisc) +{ + qdisc->__state |= __QDISC___STATE_THROTTLED; +} + +static inline void qdisc_unthrottled(struct Qdisc *qdisc) +{ + qdisc->__state &= ~__QDISC___STATE_THROTTLED; } struct Qdisc_class_ops { @@ -331,8 +350,8 @@ extern struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, struct Qdisc_ops *ops); extern struct Qdisc *qdisc_create_dflt(struct netdev_queue *dev_queue, struct Qdisc_ops *ops, u32 parentid); -extern void qdisc_calculate_pkt_len(struct sk_buff *skb, - struct qdisc_size_table *stab); +extern void __qdisc_calculate_pkt_len(struct sk_buff *skb, + const struct qdisc_size_table *stab); extern void tcf_destroy(struct tcf_proto *tp); extern void tcf_destroy_chain(struct tcf_proto **fl); @@ -411,12 +430,20 @@ enum net_xmit_qdisc_t { #define net_xmit_drop_count(e) (1) #endif -static inline int qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch) +static inline void qdisc_calculate_pkt_len(struct sk_buff *skb, + const struct Qdisc *sch) { #ifdef CONFIG_NET_SCHED - if (sch->stab) - qdisc_calculate_pkt_len(skb, sch->stab); + struct qdisc_size_table *stab = rcu_dereference_bh(sch->stab); + + if (stab) + __qdisc_calculate_pkt_len(skb, stab); #endif +} + +static inline int qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch) +{ + qdisc_calculate_pkt_len(skb, sch); return sch->enqueue(skb, sch); } diff --git a/include/net/sock.h b/include/net/sock.h index bc1cf7d88ccb..e3893a2b5d25 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1191,7 +1191,7 @@ extern void sk_filter_release_rcu(struct rcu_head *rcu); static inline void sk_filter_release(struct sk_filter *fp) { if (atomic_dec_and_test(&fp->refcnt)) - call_rcu_bh(&fp->rcu, sk_filter_release_rcu); + call_rcu(&fp->rcu, sk_filter_release_rcu); } static inline void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp) diff --git a/include/net/tcp.h b/include/net/tcp.h index 38509f047382..7118668ad534 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -196,6 +196,9 @@ extern void tcp_time_wait(struct sock *sk, int state, int timeo); /* TCP thin-stream limits */ #define TCP_THIN_LINEAR_RETRIES 6 /* After 6 linear retries, do exp. backoff */ +/* TCP initial congestion window */ +#define TCP_INIT_CWND 10 + extern struct inet_timewait_death_row tcp_death_row; /* sysctl variables for tcp */ @@ -799,15 +802,6 @@ static inline __u32 tcp_current_ssthresh(const struct sock *sk) /* Use define here intentionally to get WARN_ON location shown at the caller */ #define tcp_verify_left_out(tp) WARN_ON(tcp_left_out(tp) > tp->packets_out) -/* - * Convert RFC 3390 larger initial window into an equivalent number of packets. - * This is based on the numbers specified in RFC 5681, 3.1. - */ -static inline u32 rfc3390_bytes_to_packets(const u32 smss) -{ - return smss <= 1095 ? 4 : (smss > 2190 ? 2 : 3); -} - extern void tcp_enter_cwr(struct sock *sk, const int set_ssthresh); extern __u32 tcp_init_cwnd(struct tcp_sock *tp, struct dst_entry *dst); @@ -1404,7 +1398,7 @@ extern struct request_sock_ops tcp6_request_sock_ops; extern void tcp_v4_destroy_sock(struct sock *sk); extern int tcp_v4_gso_send_check(struct sk_buff *skb); -extern struct sk_buff *tcp_tso_segment(struct sk_buff *skb, int features); +extern struct sk_buff *tcp_tso_segment(struct sk_buff *skb, u32 features); extern struct sk_buff **tcp_gro_receive(struct sk_buff **head, struct sk_buff *skb); extern struct sk_buff **tcp4_gro_receive(struct sk_buff **head, diff --git a/include/net/udp.h b/include/net/udp.h index bb967dd59bf7..e82f3a8c0f8f 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -245,5 +245,5 @@ extern void udp4_proc_exit(void); extern void udp_init(void); extern int udp4_ufo_send_check(struct sk_buff *skb); -extern struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb, int features); +extern struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb, u32 features); #endif /* _UDP_H */ |